Thoughtworks Agent/works
Thoughtworks' control plane and governed runtime for enterprise AI agents, on any cloud. It registers any model and tool, carries scoped permissions across agent handoffs, and gives a central registry with evaluations, usage analytics and cost controls. Launched June 2026.
Work at Thoughtworks Agent/works? Manage this listing
Our take
A single control plane and governed runtime for enterprise AI agents, deployable on any cloud. It registers any model or tool, carries scoped permissions across handoffs, and offers a central registry with evaluations, usage analytics and cost controls — governance built into the runtime, not bolted on. Launched June 2026.
Best for
Enterprises managing agent sprawl that need governance, cost control and visibility across clouds.
Pros
- One control plane across any cloud
- Scoped permissions travel with handoffs
- Central registry with evals and cost controls
- Build custom agents on top
Cons
- Aimed at large enterprises
- Pricing via sales
- New platform (June 2026)
How it compares
Versus single-vendor agent runtimes like Bedrock AgentCore, Agent/works pitches neutrality — any model, any tool, any cloud — with governance as the core.
Full review
Agent/works is Thoughtworks' control plane and governed runtime for enterprise AI agents, deployable on any cloud. It registers any model through a standard API, connects any tool, and delegates to a cloud's native services and trusted third-party agents, with scoped permissions that travel with each handoff.
A central registry provides visibility, evaluations, usage analytics and cost controls across every agent, model, tool and policy in the enterprise. Announced June 16, 2026 at the Databricks Data + AI Summit, it treats governance as an architectural problem built into the runtime, and serves as a foundation teams build custom agentic apps on top of.
Cloudkart Trust Graph
3.6/5- Actual Utility4/5
Source: Initial LLM-authored rubric (backfill)
- Ease of Use3/5
Source: Initial LLM-authored rubric (backfill)
- Pricing Fairness3/5
Source: Initial LLM-authored rubric (backfill)
- Reliability4/5
Source: Initial LLM-authored rubric (backfill)
- Differentiation4/5
Source: Initial LLM-authored rubric (backfill)
Scored as of . Each score is versioned and auditable; vendors cannot buy it.
How this score is set
- Editorial rubric
- Primary signal — five dimensions, 3.6/5 average.
- Community reviews
- None yet.
- Pricing verified
- Not yet verified
- Independence
- Score set by our editorial team before any affiliate relationship is considered. No vendor can buy it.
Frequently asked questions
- Is Thoughtworks Agent/works free, and how much does it cost?
- Thoughtworks Agent/works is a paid tool.
- Who is Thoughtworks Agent/works best for?
- Enterprises managing agent sprawl that need governance, cost control and visibility across clouds.
- How is Thoughtworks Agent/works rated on Cloudkart.ai?
- Thoughtworks Agent/works scores 3.6 out of 5 on the Cloudkart.ai rubric, which weighs actual utility, ease of use, pricing fairness, reliability and differentiation. Scores are set editorially and can never be bought.
Community reviews
No community reviews yet. Be the first to share how Thoughtworks Agent/works works for you.
Relevant tools
More tools in Productivity & Automation.
NotebookLM
Google's source-grounded research assistant: upload docs, PDFs and links, then ask questions, generate study guides, and turn sources into audio and video overviews. The free tier is genuinely usable; Plus raises the limits.
OpenRouter
OpenRouter is a unified API and marketplace for large language models. With one account and key you can reach 300+ models from OpenAI, Anthropic, Google, Meta, Mistral, Cohere and many smaller providers, using an OpenAI-compatible interface. It charges passthrough rates (provider cost plus a small markup) and publishes live pricing and usage-based model rankings, so you can compare options and route to the cheapest, fastest or most reliable one. It supports automatic fallback across providers and a free-model tier for experimentation; the main costs to watch are a 5.5% credit-card fee, which hits small top-ups hardest, and a 5% bring-your-own-key fee on requests above one million per month.
Gamma
AI design tool that generates polished presentations, websites, documents, and social graphics from a prompt or outline.
Krisp
On-device AI that cancels background noise on any call and records, transcribes, and summarizes meetings with accent conversion.
Compare Thoughtworks Agent/works head-to-head: vs NotebookLM · vs OpenRouter · vs Gamma · vs Krisp