Set the intent
Define the offer, audience, voice, proof points, prohibited claims, and approval rules. This is the human context the agent should not have to rediscover.
memory → audience → boundariesHow it works / the handoff
Intent in.
Clarity out.
A useful agent does not just produce activity. It carries the brief through research, preparation, review, action, and the reply that changes the next step.
Read the agent contract ↗CONCEPTUAL WORKFLOW
brief→research→preview→review
Illustrative sequence · not live runtime evidence01 / The path
One thread,
fewer blind spots.
Research with a boundary
Request a bounded lead or account pack. The result carries provenance, freshness, confidence, suppression eligibility, and a review state.
source → evidence → candidate statePrepare, then preview
Draft a sequence from approved context. Validate variables and risky claims. The preview shows affected leads, warnings, and an evidence identifier.
draft → validate → dry-run receiptApprove the edge
Readiness, limits, suppression, and human approval determine whether an action may move forward. If the gate fails, the system returns a typed reason.
policy → approval → apply or holdTurn replies into next actions
Ingest a reply, classify it, stop a sequence where appropriate, and create a next action with enough context for a person to decide quickly.
reply → classification → next actionThe point
“The agent did the middle. The team still knows what happened.”
A design principle for delegation, not a customer testimonial.
Your workflow is different