Skip to Main Content
Events
SearchSign In

Global Codex Hackathon: [London]

Apr 15, 2026 · London, UK

Event Page
Event Page

Capco

Sentra is a real-time decision intelligence layer embedded in retail banking frontline interactions. It transforms fragmented customer data into a dynamic “digital twin,” enabling agents to understand customer context, assess vulnerability, and take the most appropriate action (proactively or during live interaction). Key Features: - Digital Twin: Real-time, contextual view of the customer (financial, behavioural, interaction signals) - Vulnerability Assessment: Explainable identification of financial stress and customer risk with clear guardrails - Intelligent Orchestration: Dynamic next-best-actions, including recommendations, suppression of harmful offers, and tailored guidance - Agent Interface: Real-time prompts, reasoning, and suggested actions during calls

According to the FCA, over 50% of UK adults have at least 1 vulnerability characteristic. 13 million people still rely on physical branches / in person banking support. At the same time, retail banking agents currently operate with fragmented data, limited context, and increasing regulatory pressure, leading to inconsistent decisions, missed vulnerability signals, and potential customer harm. This solution solves that problem by providing real-time, explainable decision support, enabling agents to make consistent, compliant, and proactive customer-centric decisions./…
0

catalyst

In Common is an AI-powered workforce intelligence prototype that helps large organizations staff teams faster, more fairly, and with better evidence. It sits on top of existing workday employee and role data, enriches static profiles through conversational AI, and uses a layered matching pipeline to connect people to opportunities. Key features: Conversational profile enrichment to capture hidden skills, motivations, working style, and team dynamics Role-to-candidate and candidate-to-role matching Hard filters plus semantic matching plus LLM-powered reasoning Anonymized shortlists by default to reduce bias and fairer Staffability scoring and training recommendations to improve deployability Decision traces and audit logs for explainability and trust

In large organizations, staffing often relies on incomplete profiles, keyword searches, and personal networks. That creates slow staffing cycles, missed opportunities, and unfair visibility for talent outside existing circles. In Common solves this by turning static workforce data into explainable, AI-driven talent intelligence that surfaces stronger matches, identifies skill gaps, and helps build teams based on capability, availability, and collaboration signals rather than proximity or guesswork./…
0

Cognita Reply

Our project combines an agent-driven development framework (AI-Led SDLC) with a plugin called LegacyBridge to enable interaction with legacy systems that lack APIs. LegacyBridge allows agents to extract context from legacy interfaces and execute actions directly within them using tools like Playwright. This replaces traditional RPA with more flexible, intelligent, and adaptive agent-based automation. Key features include: Context extraction from inaccessible or legacy systems Agent-based interaction (navigation, form filling, workflow execution) Integration with development tools (Jira, Confluence, repos, Stitch & Figma) End-to-end delivery enabled by AI-Led SDLC Reusable across multiple industries and systems

Legacy systems are a major barrier to innovation across the tech industry. Many critical platforms lack APIs or modern integrations, making it difficult to access data, automate workflows, or build AI-powered solutions. Our project solves this by enabling agents to both understand and act within legacy systems, removing the dependency on APIs and overcoming the limitations of traditional RPA./…
0

Works On My Machine

Coachdex is a team intelligence layer on top of Codex. It turns isolated Codex sessions into shared team intelligence and reusable skills by capturing developer activity, extracting patterns, and surfacing four core capabilities: Sharing, Insights, Coaching, and Suggestions. Teams can explore synced Codex sessions across repos and machines, identify repeated workflows, generate coaching recommendations, and promote successful patterns into reusable playbooks, prompt templates, and draft skills.

AI coding tools are creating value, but most of that value is trapped inside individual, ephemeral sessions. Developers each discover their own prompts, workflows, and habits, but teams cannot easily see what is working, standardise it, or reuse it. Coachdex solves this by converting ad hoc AI-assisted work into repeatable execution, measurable insights, and reusable institutional knowledge./…
0

Endavans

Our project is an AI-powered travel insurance claim processing platform that automates the full claims journey from document intake to final decision. It uses a multi-agent pipeline to ingest claim files, extract and validate evidence, reason over policy coverage, run compliance and fraud checks, make an approve/deny/escalate decision, and handle payment and customer notification. The product also includes a polished real-time dashboard with live agent activity, history, and replay, making the whole process transparent and easy to follow.

What we are solving, is the slow, manual, and inconsistent process of handling insurance claims. Today, claims teams often spend days or weeks reviewing documents, checking policy terms, validating evidence, screening for fraud, and coordinating next steps. We tackled this problem by building an end-to-end workflow that cuts manual effort, accelerates decisions, and brings full visibility into the claims process./…
0

CGI - HMCTS

An AI-powered software engineering assurance tool that turns a public GitHub repository into a structured review in minutes. A user submits a repo URL and the app clones the repository, runs a Codex(SDK)-driven assurance workflow, and produces a dashboard-backed report with weighted RAG scores across four pillars: security, maintainability, reliability, and architecture alignment. The output includes evidence-based findings, strengths, quick wins, and next steps, giving teams a repeatable and auditable alternative to manual review panels.

Software assurance reviews are slow, expensive, and inconsistent because they depend on manual evidence gathering and senior specialist time. In our client’s current model, a single review can take around five days end-to-end, and involves multiple senior reviewers and can result in bias. Our project compresses that process into an automated workflow that applies the same assessment structure every time, surfaces evidence directly from the repository, and gives decision-makers a faster starting point for governance and delivery discussions./…
0

CGI - HRS

This project focuses on developing a Time and Attendance system that integrates alongside our existing payroll platform, bringing a critical function in-house to improve control, efficiency, and data consistency. The solution includes a user-friendly frontend application where employees can securely log in, view company-specific theming, and receive prompts for upcoming timesheet submissions. Users can enter their working hours, selecting from both project-specific codes and general activity codes, ensuring accurate and flexible time tracking. A key feature of the platform is its ability to integrate multiple data sources. Where available, external systems such as Jira or card-based sign-in systems can supply attendance data. This data is processed through a microservices-based architecture, enabling each data source to be handled independently. As an example, a card reader microservice has been developed that takes raw CSV input and converts it into a standardised JSON format. This format is then consumed by a central backend API, which stores and serves the data for frontend use (currently using JSON as a working model, with database integration planned). This architecture provides a centralised data platform while remaining highly flexible. It allows the system to ingest, transform, and unify data from multiple sources, ensuring consistency across the organisation while supporting different attendance capture methods. Overall, the solution is designed to be scalable, modular, and extensible, creating a strong foundation for future enhancements and broader adoption across teams and clients.

This project addresses a direct and well-recognised business issue. As an organisation, we process approximately 2.5 million electronic payslips annually, yet Time and Attendance (T&A) is often handled through external systems. Clients have highlighted the inefficiencies of managing T&A separately from payroll, creating fragmentation in a process that should be tightly integrated. This separation not only impacts user experience but also represents a missed revenue opportunity, as we are not currently providing a fully end-to-end HRS solution despite already delivering the majority of it. A key challenge is that this cannot be approached as a “big bang” migration. Clients already use a variety of T&A systems, and forcing them to switch entirely would create friction and limit adoption. Therefore, flexibility is critical. Our approach is to build a centralised, extensible platform that can accept data from multiple sources. By supporting different input methods such as manual entry, third-party systems, and hardware-based solutions, we enable clients to integrate with our platform in a way that suits their existing processes. This ensures we remain adaptable as a business, while gradually bringing more capability in-house. More broadly, this highlights a gap in our current HRS offering. While we can deliver many payroll processes today, T&A and other HR process remains a key missing component. We believe agentic AI can play a role in accelerating the development of these additional HR capabilities, starting with Time and Attendance. Ultimately, this project responds directly to client feedback, solves a real operational problem, and creates a pathway to expand our HRS platform into a more complete, revenue-generating solution./…
0

ML6

SkillPilot is an AI-powered engineering learning platform that adapts to each engineer’s skill level, role, and growth goals. It helps in onboarding and upskilling engineers across the spectrum identify development gaps and next steps in areas such as technical depth, production readiness, code quality, evaluation rigor, collaboration, communication, mentoring, and leadership. To do that, SkillPilot can learn from various enterprise signals like pull requests, mentor-mentee input, project feedback, retrospective notes, internal knowledge bases, as well as personal info and predefined growth paths. By turning those fragmented inputs into personalized growth journeys, SkillPilot helps organizations move faster toward an AI-native way of working: engineers do not just get generic learning content, but contextual guidance based on how work actually happens inside the company. This also accelerates enterprise rollout of tools like Codex, because it helps teams learn where AI can create leverage, teaches people how to use those tools in role-relevant ways, and reinforces company-specific best practices, guardrails, and feedback loops. In that sense, SkillPilot is not just a learning product; it is an enablement layer for enterprise AI adoption. It uses Trust-by-Design principles so recommendations are explainable, humans stay in control, and feedback continuously improves both learning outcomes and responsible AI usage.

Engineering growth in enterprises is still fragmented, reactive, and difficult to personalize at scale. Useful signals are spread across PRs, retrospectives, mentorship conversations, project reviews, documentation, and capability frameworks, but they are rarely connected into one adaptive system. As a result, engineers do not always know which skills to build next, managers repeat the same coaching manually, and onboarding new joiners takes longer than it should because critical guidance, context, and resources are scattered across people and tools. SkillPilot solves this by transforming real work signals into personalized learning paths that help engineers improve where it matters most for their role and level, while also accelerating onboarding by giving new joiners a clearer, context-aware path to ramp up faster. At the same time, it makes the rollout of tools like Codex more effective by embedding them into day-to-day growth, feedback, and delivery workflows instead of treating them as standalone tools that employees have to figure out on their own. Why we built this We built SkillPilot because the need for scalable, contextual learning is becoming urgent in fast-growing engineering organizations. Adding 10% more people to the team in a single week really put our onboarding and mentoring capacity to the test. The workload is tangible: senior engineers and managers spend significant time repeating guidance, pointing people to the right resources, and translating feedback into development actions. That onboarding challenge revealed a broader opportunity. The same fragmentation does not only affect new joiners, but engineers at every seniority level who are trying to grow in technical, delivery, collaboration, or leadership skills. SkillPilot was built to turn that manual, inconsistent process into an AI-native learning workflow that scales mentorship, shortens onboarding time for new joiners, and supports continuous development across the organization./…
0

SIA-01

Our project is an artifact and integration-driven modernization framework designed to transform legacy applications into modern architectures safely and incrementally using structured, multi-agent workflows using Codex.

Current agentic coding tools struggle with long-running legacy modernization: as context grows, they lose track of architecture, miss dependencies, and cannot reliably resume after interruptions. Codex Phoenix solves this by replacing fragile chat-based workflows with an artifact-driven, structured pipeline that preserves state, understands dependencies, and enables safe, incremental, and fully resumable modernization of large codebases./…
0

deepsense.ai

Our project aims to create a set of hierarchical skills for migrating legacy Python code bases using Codex and subagents. By having more modular skills we are able to delegate work from a higher-level abstraction skill to more implementation oriented skills. The goal is to keep the same functionality and feel of the application whilst improving the underlying tech stack.

Often there are projects that were created in the past, could still be useful, and would be more performant by running on a more modern stack. This still require human-in-the to keep the control over the process./…
0

Artefact

Upload a proposal deck and walk away. A short while later, you'll have a shareable link to a fully deployed proof of concept on AWS - built to Artefact's engineering standards, ready to demo to a client or hand directly to the technical team for production.

Winning new work requires demos. Building demos requires engineers. And engineers are always underwater. Off-the-shelf tools like Replit and Lovable let non-technical users ship something fast - but the output is throwaway code that can't be handed to an engineering team. Coding agents like Codex produce genuinely high-quality output, but require technical knowledge to deploy. We close that gap. Our system handles the entire technical pipeline automatically: generating code, building containers, pushing to GitHub, and deploying to AWS - all triggered by a simple PowerPoint upload. Because we build with best practices (including SKILL.md files), the output isn't a prototype to be discarded - it's a foundation the tech team can actually build on. No spaghetti code, no rework, no bottleneck./…
0

SIA-2

Today, tools like Codex already let you split development into multiple worktrees per feature. But merging those worktrees is still a manual, slow process: you create PRs, wait for human review, and merge step by step. What we’re building is a mastermind layer on top of that. Instead of treating worktrees independently, the mastermind orchestrates them: It manages multiple parallel worktrees automatically It handles merges between them without heavy manual intervention And most importantly, it enables combinatorial testing of features Concretely, if you have Feature A in Worktree A and Feature B in Worktree B, you can instantly spin up a combined environment (A + B), test them together, and validate that they actually work as a system—not just in isolation. The mastermind coordinates these combinations, merges the compatible ones, and keeps everything else isolated and reversible. In short: 👉 From manual, linear merging → to automated, parallel, and composable development. For the demo, we’re using Strudel because it represents a real, tangible codebase—but in a way that’s intuitive. In Strudel, features are like music tracks: bass, drums, melody, etc. Each track can have multiple variations, just like different implementations of a feature. Instead of working on a single version, we generate multiple possibilities per track. Users can then listen to and combine these variations in real time: Bass v1 with Drums v2 Melody v3 with Bass v2 or any combination they want This is exactly like combining features from different worktrees. On top of that, the mastermind orchestrates everything: It manages all these parallel “tracks” (worktrees) It enables seamless combination and testing of them together And it helps surface the best overall composition, not just the best individual parts So instead of validating features in isolation, you experience and evaluate them as a system, just like music. In short: 👉 Features become tracks 👉 Worktrees become variations 👉 And the mastermind becomes the composer optimizing the final piece

Parallel development exists, but integration is still manual and linear. Merging, testing, and validating features together is slow, error-prone, and happens too late so teams optimize in isolation instead of as a system./…
0

statworx

TalentLens is an AI-powered CV screening solution that transforms unstructured resumes into structured, comparable candidate profiles. It enables faster, more consistent hiring decisions through standardized evaluations, evidence-backed skill assessments, and transparent scoring. Key features: - LLM-based extraction of relevant skills and requirements directly from job postings - Converts PDF resumes into structured candidate profiles using LLM-based parsing and information extraction - Generates evidence-backed assessments of skills and experience from CV content - Scores candidate fit against role requirements to highlight the most promising matches

Recruiters often receive hundreds of CVs in different formats, with inconsistent wording and varying levels of detail. This makes early screening slow, repetitive, and subjective. TalentLens solves this by: - reducing the time spent manually interpreting CVs - making candidates more directly comparable across recruiters and roles - grounding skill assessments in actual evidence instead of self-reporting alone/…
0

Cartograph

Using Codex to prototype a Codex-powered solution focussed on data migrations, particularly around semantic reasoning over legacy databases

In large enterprise data migration exercises, business and domain knowledge around databases, especially poorly documented or old ones, tends to be locked behind clients. Discovery and analysis workshops are time consuming and cause programmes to drag on. Our project is a rapidly deployable prototype that showcases how Codex helps reduce friction and provide a user-friendly interface to expedite using client knowledge as part of the migration process./…
0

Capgemini Team 1 (Codex Morph)

Our Project - Codex Morph is a Codex-powered legacy/POC discovery and transformation planning workflow that turns a codebase into a structured, developer-ready modernisation plan in minutes. The product is built as a guided Next.js workspace with a multi-agent planning engine behind it. A user submits a codebase and transformation brief, Codex analyses the system, asks targeted clarification questions, orchestrates specialist section agents, and produces a reviewable transformation output covering architecture, migration strategy, security, CI/CD, testing, integration, product planning, and publish-ready documentation. What makes the approach strong is that Codex is not used as a one-off assistant. It is the workflow engine. It handles large codebase analysis, maintains context across multiple planning stages, and uses compaction patterns to preserve context for later iterations. Each run persists local Markdown artifacts such as shared run context, per-agent `context.md`, and `output.md` files so the system can rehydrate only the relevant context on reruns instead of starting from scratch. That makes the workflow more reliable, iterative, and reusable across delivery engagements. Key features: - Codebase intake from GitHub URL, ZIP upload, or local folder - Guided clarification flow before planning starts - Multi-agent planning orchestration using the Agents SDK - Specialist section agents for architecture, migration, infrastructure, security, testing, database, integrations, and product delivery - Local artifact generation for context persistence and future iteration - Human-in-the-loop review, section updates, and targeted reruns - Publish-ready outputs including hosted report views and structured export paths This is designed as a reusable accelerator, not a one-off demo. The workflow can be applied to different codebases, different transformation briefs, and different partner scenarios with the same structure: - Intake - Clarification - Multi-agent analysis - Review - Publish Because context persisted in local artifacts and outputs are modular by section, the system is well suited to repeated use across discovery engagements, internal accelerators, and future productisation. It can evolve into a partner-facing modernisation assessment tool, an internal engineering accelerator, or a pre-sales and delivery discovery workflow.

Both, Modernisation and MVP to production work often stalls before delivery begins because teams do not have a clear, shared view of what already exists. Legacy systems, internal tools, and early-stage prototypes are usually under-documented, inconsistently structured, and difficult to reason about at scale. Teams lose weeks reverse-engineering architecture, dependencies, risks, and migration options before they can even agree on a plan. This project removes that bottleneck. It uses Codex to analyse large codebases, maintain working context across multiple files and planning stages, and convert that analysis into a structured transformation blueprint. Instead of starting with scattered tribal knowledge and manual discovery, teams get an evidence-backed current state, target state, phased roadmap, risks, and next actions. For internal partner teams, that means faster discovery, clearer technical alignment, better handoffs, and a reusable accelerator for transformation engagements./…
0

BCG-2: Briefly.ai

Our project is Briefly.ai, a personalized news product for people who need to keep up with the fast-moving agentic AI ecosystem without drowning in noise. It combines a user preference profile with a relevance-ranked briefing feed, so each person sees updates tailored to the topics, vendors, products, and tools they actually care about. Key features include personalized onboarding, saved interest profiles, role-aware summary styles, a filtered briefing feed, and a verification panel that shows the original source, supporting references, and trust signals behind each update.

Agentic AI news is fragmented, high-volume, and difficult to verify. People currently have to scan many sources to figure out what changed, what matters to their work, and whether a claim is trustworthy. Our project solves that by turning scattered updates into a concise, personalized, and source-aware briefing experience./…
0
+1

Unit8_Switzerland

Codex Compliance is a plugin that extends Codex into a compliance-aware coding agent for regulated industries. It scans codebases against frameworks like HIPAA, GxP, and the EU AI Act, identifies compliance gaps, suggests and applies fixes, and generates audit-ready evidence. By embedding compliance directly into the development workflow, it enables organizations to safely adopt AI coding agents, reduce manual reviews, and accelerate delivery in high-stakes environments. Note: Video shows as 8 min but is only 1.:12min long

AI coding agents can generate code quickly, but regulated industries cannot safely adopt them because there is no reliable way to verify that the code is compliant with frameworks like HIPAA, GxP, or the EU AI Act. Our project solves this by automatically detecting, fixing, and generating evidence for compliance gaps directly in the coding workflow. Its using multiple levels of sub agents for identifying issues and fixing them./…
0

CodexTree

Codex Tree is a branch-aware environment for AI-assisted software development. It turns a normally linear Codex chat into a tree of connected conversations so users can split a complex task into separate branches, keep the right context in each branch, and still merge the results back together later. The project includes a VS Code custom editor that visualizes the workflow as a tree and a Python backend that manages the actual branch sessions against a target codebase. The core idea is that software work is rarely linear. A user might ask Codex to plan an app, then break that work into branches such as API, UI, tests, or bug fixes. Each branch inherits the relevant prior context, maintains its own chat history, and runs in its own git-backed worktree so filesystem changes stay isolated. This avoids the common workflow of creating a new feature branch, starting a brand new AI session, and then re-prompting the model with all of the same background context just to continue related work. When work is complete, Codex can merge branches back into a new combined branch using both the branch workspaces and the saved conversation histories as context. Key features include visual tree-based chat editing in VS Code, branch creation from the current tip, the root, earlier turns, or specific nodes, per-branch filesystem snapshots and rollback, persisted session state, Codex-driven branch merges, streaming runtime events for assistant output, commands, tools, and file changes, command and file-change approval handling, and the ability to adjust model and reasoning level across turns. Compared with the regular Codex app fork and worktree logic, Codex Tree adds a much more usable layer on top: branches are visible as part of one connected workflow, branch points are tied to conversation nodes rather than being managed as isolated threads, users can branch from historical points with matching filesystem state, and rolling back a branch restores both the chat history and the files together. In the regular Codex app, once a fork is made the relationship to the original chat is much easier to lose because it appears as a separate chat thread. In Codex Tree, that relationship stays visible as a linked branch in the same view, so related ideas, experiments, and follow-up work remain grouped together instead of being scattered across separate chats. The visual tree also makes it much easier to keep track of what branches exist, what conversations happened in each branch, what was done, and roughly when different lines of work diverged or were completed. Because the interface is graphical and user-friendly, it can also make complex coding workflows more accessible to non-technical or less technical users who may find a purely terminal- or chat-driven workflow harder to follow. The graphical display makes plans, ideas, and workflow structure easier to explain, present, and understand. Together, these features make Codex feel less like a single chat window and more like a structured workspace for managing parallel AI development workflows.

Most AI coding tools force complex development work into one long linear conversation. That makes it hard to explore multiple approaches, separate independent tasks, preserve the right context for each thread of work, and safely manage code changes across experiments. As the conversation grows, useful context gets buried, unrelated ideas get mixed together, and it becomes difficult to return to earlier points or combine parallel work cleanly. In many current workflows, if a developer wants to split work into a new feature path, they often have to open a new session and repeat the original prompt and context again, which is slow, repetitive, and error-prone. Codex Tree solves this by giving AI conversations the same kind of branching structure that developers already use in version control. Users can fork work into focused branches without duplicating prompts, keep each branch tied to its own workspace and history, roll back safely, and merge results intentionally. If part of the chat stops being useful or reaches a dead end, users can roll back to an earlier point and create a new branch from there rather than restarting from scratch. It also becomes easy to test two different approaches in parallel by creating a branch for each option, exploring both independently, and then continuing with whichever approach works better. Compared with using the regular Codex app fork and worktree features directly, this project reduces manual session management, keeps the branch relationships visible instead of letting forks disappear into separate chats, preserves the exact filesystem snapshot associated with each branch point, and makes branch history easier to understand and revisit. It also gives users a visual map of their branches and chats, improving visibility into what has already been explored and how the work evolved over time. This creates a more natural way to plan, delegate, compare alternatives, and coordinate larger builds with Codex./…
0

Accenture 1 (CEE)

A key advantage for regulated industries: the framework only optimizes the pipeline logic itself — no data ever leaves the client environment. This makes it directly applicable to healthcare, legal, and financial clients who are required to run local, on-premise models due to data privacy regulations. Weaker local models become significantly more capable through autonomous iteration — without any data exposure.

Getting an pipeline to work is fast. Making it reliable, robust, and production-ready is slow — it requires repeated manual cycles of testing, tweaking, and re-evaluating. This framework hands that entire iteration process to Codex. It doesn't just assist with one change — it runs the full improve-evaluate cycle autonomously, addressing edge cases, inconsistencies, and failure modes that a developer would otherwise spend weeks hunting down manually./…
0

Cap Invent

Loqui is an agentic interview platform for capturing human knowledge at scale. It helps teams turn a rough research brief into a deployable interview mission, schedule and run adaptive AI-led interviews in parallel, and convert those conversations into a structured, auditable insight graph. Key features include mission intake from natural language, an Agent Studio for refining interview objectives and target lists, adaptive interview execution over chat or voice, a deployment cockpit for tracking response and completion rates, and an insight layer that links findings back to source interviews so teams can drill down, interrogate the data, and generate outputs like executive summaries or slide decks.

A huge amount of valuable knowledge inside organizations never makes it into systems or documentation. It lives in people’s heads, especially with experienced staff, specialists, consultants, and operators. When those people leave, retire, or are simply too busy to interview properly, that knowledge is lost. Existing options force a tradeoff: surveys scale but are shallow, while human interviews are rich but slow, expensive, and hard to synthesize. Loqui solves this by making qualitative interviews scalable, adaptive, and structured, so organizations can capture human insight faster without losing depth./…
0

PwC-2

We have built a product which will allow users of applications in the early stages of development to report bugs and issues they find with the system. An agentic system in the background will then attempt to recreate the bug, find the probable cause of said bug and then create a plan to fix the bug. The agentic system will then test the proposed fix, and should it work create a PR on the repository to implement said changes. This ultimately will greatly streamline the process of bug -> patch in the software development lifecycle.

We aim to solve the problem of early stage products iteration lifecycle being streamlined and improved by optimising and automating the way bugs are reported and dealt with./…
0

Slalom Germany

A self-hostable M&A intelligence platform, allowing M&A analysts to perform their required initial due diligence and strategic fit assessment for potential target companies in minutes instead of days. Key features are: 1) Mini-CRM to store data on target companies 2) Automated research workflow that integrated web deep resaearch (powered by OpenAI models) and data from various company research APIs (e.g., SEC, EDGAR, Companies House, OpenSanctions). 3) Ability for user to upload strategy documentation of the acquiring company 4) Ability for user to set and define strategy fit criteria 5) Automated strategy fit assessment workflow that utilizes the automatically generated research, proprietary company strategy documentation and the strategy fit criteria to run an initial strategy fit assessment (powered by OpenAI models).

M&A analysts usually spend a lot of manual effort in collecting information on potential target companies that may be interesting for deeper investigation. This means they can conduct a maximum of 10 analyses per week, if this were their only task. In addition, corporations are highly unwilling to share their sensitive company strategy information with SaaS providers. With the Slalom Germany M&A Research & Analysis platform, users can now run 1000s analyses per week, thus improving their ability to cover all potential targets, and filter out uninteresting candidates with much higher speed. In addition, the self-hostable nature ensures that secret and highly sensitive strategy documentation remains on the acquirer's servers./…
0

Quantum Black

This project reimagines what it feels like to explore a city on foot. Instead of opening a map, searching for landmarks, and piecing together your own route, the user simply drops themselves anywhere they want to begin. From that moment, the app becomes a live AI tour companion: it understands the chosen starting point, builds a personalized walking or running route around it, and guides the user forward through spoken narration, interactive map pins, and timely nudges as they move.

Most city exploration tools are static, generic, and require users to manually search, read, and plan. Our project makes urban discovery feel effortless and immersive by generating a personalized tour around wherever the user actually is, then guiding them with audio and map-based interaction in real time. It removes the friction between “I want to explore” and “I know exactly where to go and what to listen to/…
0

CXecuters

CXecute accelerates contact center agentification by turning customer support transcripts and enterprise API specs into a deployment-ready Google Gemini Enterprise for Customer Experience GECX package. Instead of spending months manually moving from discovery to deployment, teams can use CXecute to automate the path from customer conversations and backend systems to validated AI agent artifacts. Key features: automated intent discovery from support transcripts API-to-intent mapping from enterprise specs payload flattening for agent-ready context generation of a real GECX package validation and self-repair loops when issues are found gateway bundle generation for deployment readiness live orchestration dashboard with stage status, logs, and agent handoffs

The biggest barrier to enterprise customer service AI is not the model, but the delivery workflow before deployment. Teams still spend months discovering intents, mapping APIs, shaping data, configuring platforms, and validating outputs. CXecute automates that workflow, reducing time-to-deployment and making agent delivery faster, more repeatable, and less dependent on manual coordination./…
0

SpringGuard

SpringGuard is an agent-native SDLC workflow for reducing a bounded static-analysis backlog in Spring Boot repositories. It uses a real Java codebase, a curated SonarQube issue set, repo-local instructions, and hook-driven validation so Codex can fix a narrow set of issues without widening scope. Key features are bounded remediation in the target repo, fast compile and static-analysis checks inside the agent loop, SonarQube checkpoint rescans, durable repo-local SDLC artifacts under `.agent-sdlc/`, and a reusable plugin that carries the workflow to the next repository.

Teams already have quality signals, but those signals are usually disconnected from execution. SonarQube, Checkstyle, and SpotBugs can identify the work, yet engineers still have to manually clear static-analysis backlog items one by one, and unconstrained agents can drift beyond the intended scope. SpringGuard solves that by turning quality tooling into a guarded remediation loop: Codex fixes a curated issue set inside repo boundaries, receives immediate hook feedback after edits, and uses SonarQube as the checkpoint and review surface while durable SDLC artifacts keep the work traceable./…
0

BCG-1

Domino is a dependency-upgrade impact analyzer for Python codebases. Given a package and a version change, it builds a static dependency graph across the repo, diffs the package API between versions, matches the changed symbols to real code usage, and shows the blast radius across files, callers, tests, and entrypoints. It outputs a conservative upgrade verdict and structured evidence, and uses Codex to explain the findings in plain English.

Dependency upgrades are risky because developers usually do not know what will break until after they make the change. Reading changelogs and grepping a codebase is slow, incomplete, and hard to trust in larger systems. Domino solves this by showing exactly where a changed or removed API is used, what internal code depends on it, and how safe the upgrade is likely to be before the developer merges anything./…
0

Mck-Rana

One command palette for every internal tool. Built for the McKinsey intranet, this product helps teams navigate fragmented internal and proprietary products by turning enterprise tools into plugins inside one unified, system-level command palette with a fast keyboard entry point.

Current state Fragmented intranet products and bookmarked URLs to reach the right destination GUI-heavy workflows that force too many clicks through menus and forms Tribal knowledge needed to discover the right McKinsey tool or workflow/…
0

Capgemini 1

Agentic Data Migration Engine is a Codex-powered demo that turns a legacy user-domain schema into an inspectable migration specification and deterministic SQL. It orchestrates four agentic phases: schema inference from DuckDB fixtures, semantic enrichment grounded in profiling and target-model documentation, mapping generation with explicit transformation intent and approval state, and SQL compilation. Key features include a Kuzu graph-based digital twin, per-phase Markdown reports, JSONL audit logging, a machine-readable approval artifact, and compiled SQL models for dim_user, dim_role, bridge_user_role, and dim_address.

Large-scale data migration projects are still slow, expert-heavy, and difficult to govern because teams must manually reverse-engineer schemas, reason through ambiguous mappings, document decisions, and translate that work into executable migration artifacts. This project brings the power of agent-driven data migration to that process: it accelerates schema understanding, semantic interpretation, mapping design, and SQL generation, while keeping human approval, auditability, and delivery control in place. The result is faster migration analysis, quicker iteration cycles, and more trustworthy handoff artifacts for delivery teams./…
0

Cognizant - CogniSense

Touchless Control Assistant is a hands-free presentation and meeting controller powered by gestures, voice, and presence awareness. It lets a user move slides, pause or resume, mute audio, and track actions without touching a keyboard or mouse. Key features: Gesture-based slide navigation Voice commands for next, back, mute, start, and stop Away-state detection with visible pause status Unified command router for gesture and voice inputs Live event log with command, action, source, and timestamp Reusable architecture for accessibility and frontline workflows Extendable for other domains

The project solves the problem that meetings, demos, and accessibility-sensitive workflows still depend too heavily on keyboard and mouse interaction, even when hands-free control would be faster, more inclusive, and more practical. It gives users a touchless way to control presentation and meeting actions using voice, hand gestures, and presence awareness through one reusable multimodal command system./…
0

CGI Leeds

A self-healing PR Guardian

Helping use sub-agents to provide better PR feedback. Alas the working demo was not possible but we learned a lot about EU data residency vs GitHub Action running in the US :D/…
0

Prompt, Hallucinate, Deploy

Context-aware discovery and recommendation tool that turns natural-language data requests into actionable guidance for data teams. It analyzes an organization’s existing datasets, schemas, and pipelines to identify what can be reused and suggest what needs to be created when reusable components do not already exist.

Data teams often waste time duplicating work because existing data assets are difficult to discover across systems, teams, and documentation. This leads to redundant pipelines, inconsistent implementation decisions, and slower delivery of new data use cases. This tool solves this by helping teams quickly understand what already exists, what can be reused, and where new work is actually needed./…
0