Agent Team template
A browser-only team that reviews explicitly selected local documents, separates evidence from assumptions, and produces an owner-ready brief without connected apps or managed infrastructure.
One-message setup · 3 specialists · Live after setup
Designed for
Founders, operators, analysts, and technical teams reviewing private notes, exports, specs, or repository documentation
Outcome
Turn a reviewed set of local files into a concise, evidence-linked brief while keeping orchestration, checkpoints, and artifacts on this device.
Say what should be true when the work is done.
Codelit runs one labeled Sample with no account, model, or external App calls.
Review the evidence, then reuse the same brief with your data when it is useful.
Extracts facts, decisions, dates, and open questions from only the reviewed excerpts.
Fast long-context model
Finds themes, conflicts, risks, and opportunities across the evidence ledger.
Reasoning model
Turns validated findings into a concise action brief for the intended audience.
High-quality writing model
Loads the workflow goal, allowed actions, escalation policy, and output contract before the agent plans work.
Turns explicitly reviewed local excerpts into a source-linked brief without connected or managed tools.
Centralizes high-risk action checks for writes, secrets, customer data, billing, deploys, and public communications.
List the reviewed files, extract material facts, and attach each fact to its source path.
Group evidence into findings, contradictions, risks, opportunities, and unanswered questions.
Write a concise brief with source-linked findings, caveats, and practical next actions.
Open it in Codelit and describe the result. Codelit handles common setup while Flow stays available for direct editing and Activity keeps the proof.
Use this teamReads one release channel, prepares a concise owner-ready update, pauses on the exact message, posts it once, and returns Slack delivery proof.
Reviews recent deployments for one project, pauses before spending build resources, creates one preview from the latest source, and returns its deployment evidence.
Reads one repository's open issues, drafts an evidence-backed follow-up, pauses on the exact issue comment, posts it once, and returns the comment proof.