ExponenLabsExponenLabs

Free tools: try our work before you talk to us

Tools you can use on your own, today, at whatever stage of AI adoption you are in. They are the same tools we use when we run the method with clients, and the internal ones are open source, so you can judge our work before you ever talk to us.

  • Self-serve
    Use it on your own, today, in a few minutes.
  • Open source
    Our internal tooling. Read the code, run it yourself.
  • Installed with the method
    Set up inside your company during the partnership, such as guardrails and the agent register.

Where are you today?

Pick the phase that sounds like you and start with its tool.

  1. Phase 1

    Discover & Assess

    “Where do we stand?”

    Curious about AI, not sure where it fits yet.

  2. Phase 2

    Plan & Budget

    “What do we do first, and what will it cost?”

    Ready to act, and need a plan you can defend.

  3. Phase 3

    Design & Build

    “How do we build it properly?”

    Building now, or about to, and want it done right.

  4. Phase 4

    Review & Improve

    “Is it working, and how do we make it better?”

    AI is live and now has to earn its keep.

Then the loop: what each phase teaches you updates the plan.

Every tool, in lifecycle order

Explore our free tools and open-source packages grouped by where you are in your AI journey.

Phase 1

Discover & Assess

“Where do we stand?”·Curious about AI, not sure where it fits yet.

1 tool

AI Scorecard

Self-serve

Two self-audits in one: AI-Readiness (data, tools, team) and AI-Native Readiness (use-case fit, human + AI design, operating model).

Founders new to AITeams with AI tools but no planBefore a first call
What you get
  • AI-Readiness: a straight score on your data, tools, and team
  • AI-Native Readiness: is your use case rough- or sharp-edged, and is the work built around it
  • The two or three things worth doing first, in each report
  • An optional blast-radius check on anything that already runs unattended
  • An honest note on where AI will not help you
Get your AI Scorecard (3-6 min)
NextTurn your score into a plan: AI-Native Business Deployment
Phase 2

Plan & Budget

“What do we do first, and what will it cost?”·Ready to act, and need a plan you can defend.

1 tool

AI-Native Business Deployment

Self-serve

Six plain answers become an AI operating plan: what AI runs, what people still decide, and your week-one steps.

Small & mid-size businessesOwners setting an AI budgetOps-heavy teams
What you get
  • A plan drawn out, not a list of tools to go and buy
  • Clear on what AI runs and what stays a human decision
  • The order to build it in, week by week, at your budget
  • Activate it to meet the senior lead who runs it with you
Get your AI operating plan (2 min)
NextBuild the plan properly: AI Engineering Cookbook
Phase 3

Design & Build

“How do we build it properly?”·Building now, or about to, and want it done right.

3 tools

AI Engineering Cookbook

Open source
We use it on every project

Our playbook for shipping software with AI agents: plan first, guardrails throughout, skills you can install today.

Engineering leadsTeams adopting coding agentsExisting codebases
What you get
  • Plan before you build, so the agent knows exactly what to make
  • Checks and guardrails, so nothing ships without being verified
  • Works on new projects and on codebases you already have
  • Installable skills and templates your team can use today
View on GitHubRead the guide
NextTest and improve what you ship: Recursive Agentic Improvements

Jev Playground

Open source

A simulated playground along with actual code samples and scenario-based examples for fast, typed System 1 models.

AI engineersAgent architectsBackend teams
What you get
  • 16 interactive simulations: support triage, guardrails, lead scoring, and agentic handoffs
  • Sub-200ms typed decisions using Choice, Score, and Noul primitives instead of unconstrained text
  • Runnable Python & TypeScript cookbooks for sequential, parallel, and orchestrator-worker architectures
  • Runs alongside your existing LLMs (OpenAI, Claude, Gemini) with no install or API key needed for demos
Try live demosView on GitHub
NextTest and improve agent behavior: Recursive Agentic Improvements

Hybrid Search RAG

Open source

A working example of AI search that understands meaning and still respects exact terms like part numbers.

Teams building AI assistantsSupport & catalogue searchDevelopers
What you get
  • Finds the right answer even when the customer does not use your exact wording
  • Still respects exact terms like product codes, part numbers, and names
  • Runs on your own database, so answers come from your data, not the open internet
  • Built with tools you can run yourself: CrewAI, Qdrant, Neon Postgres, and Google Gemini
View on GitHub
NextMeasure and tune your assistant: Recursive Agentic Improvements
Phase 4

Review & Improve

“Is it working, and how do we make it better?”·AI is live and now has to earn its keep.

1 tool

Recursive Agentic Improvements

Open source
We use it on every project

Scaffold an AI agent, test how it really behaves, then improve it step by step instead of guessing.

Teams with agents in productionAgent buildersQA & platform engineers
What you get
  • Three commands that create, improve, and extend an AI agent
  • Works across the main agent frameworks: Agno, CrewAI, LangGraph, and Google ADK
  • Reads the live documentation first, then writes a plan you approve before any file changes
  • Tests run offline against mocked models, so the results are repeatable
View on GitHubRead the guide
NextRe-check readiness as you scale: AI Scorecard

More coming soon

We keep building, and new tools land in their phase here as we ship them. See the method behind them.

Make your business AI-native, starting this month.

You speak to the senior lead who would do the work. If we are not the right fit, we will say so.

Book a 30-min callGet your AI operating plan (2 min)