# Guides

> Get one thing done with Kindgi, from writing a tool to releasing an agent version.

Each guide gets one thing done with Kindgi: pick an area, then the task.

A guide assumes you have done [Start](https://docs.kindgi.com/v0.1.8/start.md). Its code is in tabs, one per SDK the guide covers. Every guide was run as written against the version of Kindgi these docs describe.

- [Tools](https://docs.kindgi.com/v0.1.8/guides/tools.md): write a tool in TypeScript or Python, call an HTTP API without code, give a tool a secret, mark it read-only, and use an MCP server's tools.
- [Agents](https://docs.kindgi.com/v0.1.8/guides/agents.md): write an agent, give it input, get a typed answer, choose its model, hold a conversation and cap what a turn may spend.
- [Models](https://docs.kindgi.com/v0.1.8/guides/models.md): connect Anthropic, Gemini on Vertex AI, an OpenAI-compatible endpoint, or a model you serve yourself.
- [Flows](https://docs.kindgi.com/v0.1.8/guides/flows.md): pass data between steps, branch, loop, run steps in parallel, retry, wait for a person, and dry-run a flow.
- [Runs](https://docs.kindgi.com/v0.1.8/guides/runs.md): start runs from the CLI or your app, retry safely, follow them live (from the browser too), read their journal, cancel and list them.
- [Orgs and projects](https://docs.kindgi.com/v0.1.8/guides/projects/organize-by-org-and-project.md): give each customer an org with its projects, and run and read their work by project or org.
- [Webhooks](https://docs.kindgi.com/v0.1.8/guides/webhooks.md): get a signed `run.finished` request when a run ends, verify it in your app, and test and replay deliveries.
- [Guardrails](https://docs.kindgi.com/v0.1.8/guides/guardrails.md): check an agent's answers, give a check its settings, and choose whether a failure stops the turn.
- [Approvals](https://docs.kindgi.com/v0.1.8/guides/approvals.md): have a person approve what an agent does before it happens.
- [Secrets and env](https://docs.kindgi.com/v0.1.8/guides/secrets.md): where a pack's settings and secrets live on your machine and in a deployment, how your code gets them, and the sandbox `kindgi dev` runs it in.
- [Sign-in](https://docs.kindgi.com/v0.1.8/guides/sso/sign-in.md): sign in to the console, keep a session, and see the enterprise sign-in options Kindgi builds with you.
- [Cost and provenance](https://docs.kindgi.com/v0.1.8/guides/observability/trace-an-answer.md): trace an answer to the model and tool calls behind it, and what each call cost.
- [Evals](https://docs.kindgi.com/v0.1.8/guides/evals/judge-a-runs-output.md): judge runs' answers, build a test set from them, change a prompt or a setting without a deploy, compare the new version on the test set, and release it. You can also propose a change through review, or let a pass look for a better setting or prompt.