All agents
SalesFor pursuit teams & AEsIn build

Estimation & Margin Agent

Builds the effort estimate and margin model behind a proposal — workstreams, role/effort matrix, rate-card pricing, scenarios, and comparables from historical actuals. All arithmetic runs in the deterministic sandbox.

Estimate accuracy≤ 15% varianceGoalSign up to run

How it works

Step 1
You provide
Paste your details
Step 2
Grounds
Retrieves & cites — no ungrounded claims
Step 3
Drafts
Schema-checked, code-assembled output
Step 4
You approve
Drafts and acts on request, human approves before anything leaves

Ask it like

estimate this engagementwhat's the margin on this deal

Model & guardrails

  • Runs on MYAM shared · open 7B (Qwen) by default — you can point it at your own model.
  • Autonomy: Drafts and acts on request, human approves before anything leaves. Nothing leaves without a human’s approval.
  • Data: Restricted — tightest controls. Provenance is attached to every output.

Outcome

Estimate accuracy
≤ 15% variance
Goalour goal — not yet measured on live runs
TargetEvalPlatformVerified

Fills in as real usage proves it — from a Target we set, to Eval-measured (passes our test suite), to Platform-measured (across ≥20 accounts), to Verified (customer outcomes).

Also tracked: Margin protection vs baseline · Recomputation exactness 100%

Works well with