What FedGrade does — the capability map
This is the single reference for every capability FedGrade ships, the tier it needs, and how it behaves on provenance. The platform's hard rule runs through all of it: nothing leaves the system without a citation, and a result with thin evidence is graded down honestly rather than dressed up as confident. Tier floors below match the limits the product enforces; see Tier overview for the full table.
The provenance grades
Most capabilities below carry one of four grades on each result:
- verified — passed FedGrade's citation validation (verbatim-substring match plus a claim-support check).
- source-cited — a direct retrieval from a cited primary source; there is no synthesized claim to validate.
- modeled — pipeline-derived (entity-graph edges, rankings), with the underlying sources attached.
- insufficient-evidence — FedGrade cannot support an answer and says so instead of inventing one.
Intelligence reads
| Capability | Tier | Provenance behavior |
|---|---|---|
| Daily Brief | Free (top 3, in the app) / Pro+ (up to 10, plus email) | Every claim checked against its cited excerpt; an unsupported Brief is delivered as insufficient evidence |
| FedGrade Forecast (pre-RFP predictions) | Free (view) / Pro+ (watch individual predictions) | Rationale cited to signal ids; materialization log shows misses |
| Forecast calibration ledger | Public | Brier + reliability over resolved predictions; pre-launch status until predictions resolve |
| Search, finder, cross-entity lookups | Free+ (unmetered) | Ranked passages, each source-cited |
| Agency and vendor profiles | Free (view; predictions Pro+) | Each section a cited bundle; honest empty state when sources are thin |
| FedGrade Network graph | Pro+ (depth 1 Pro, 2 Team, 3 Enterprise/Government) | Every edge carries a source pointer; co-occurrence edges are heuristic |
| Cited network paths ("how do these connect") | Team+ | Each hop cited; uncited hops are skipped |
Capture workflow
| Capability | Tier | Provenance behavior |
|---|---|---|
| Ranked opportunity pipeline | Team+ | Decomposed rank (pWin × value × proximity × fit), each component cited; unrankable items surfaced honestly |
| pWin capture assessment | Team+ (200 / month; Enterprise+ unlimited) | Decomposed factors, each graded; grade rolls up to the weakest weighted factor |
| pWin calibration ledger | Team+ (private to your workspace) | Per-model-version Brier; never pooled, never published |
| RFP shred (solicitation → requirements) | Team+ (100 / month; Enterprise+ unlimited) | Every requirement cited to its section and character span |
| Compliance matrix (L ↔ M ↔ SOW) | Team+ | Deterministic cross-walk; gap rows flagged; every row editable |
| Intelligent alert rules | Team+ (25 rules; Enterprise 200) | Every fired alert carries the triggering event and a citation |
Bill & File (post-award)
| Capability | Tier | Provenance behavior |
|---|---|---|
| Timesheets (DCAA-shaped approval workflow) | Free+ | Every hour charges a contract or a cost pool; approval records a named human approver |
| Invoices drafted from timesheets and the GL, payment tracking | Free+ (needs a contract record — created when a pursuit is marked won) | No invented dollars: a line with no recorded rate is left blank and listed as a gap; submission is always human-authorized |
| Submission packages | Free+ (the compliance-matrix volume needs RFP shred, Team+) | Real files only, in Section-L order; a missing volume is listed as a gap, never faked |
| Compliance calendar — CPARS prep, subcontract flowdowns, SAM renewal, filing deadlines | Free+ (contract deadlines need a contract record) | Deadlines are computed by rule from each contract's own fields, plus company-level obligations you record; a capped read says so on screen |
Deliverables (exports)
| Capability | Tier | Provenance behavior |
|---|---|---|
| Brief PDF | Free+ (unmetered) | Citations as footnotes |
| Brief DOCX | Pro+ | Citations collected as footnotes, editor-friendly |
| Brief share links | Pro+ | Read-only; optional expiry and password |
| Brief deck (PPTX) | Team+ | Per-item slides + source appendix |
| Capture package (DOCX/PPTX) | Team+ | Brief + pWin + compliance matrix + agency snapshot, each section cited or honestly absent |
| Pipeline board report (DOCX/PPTX) | Team+ | Ranked pipeline with cited factor drivers + not-yet-rankable section |
| Compliance-matrix export (DOCX/XLSX) | Team+ | One row per requirement with its citation |
Trust + integrations
| Capability | Tier | Provenance behavior |
|---|---|---|
| Signed claim artifacts | Not live on any tier | Not offered. No Brief claim has been signed to date; only generated export files carry signed manifests |
Claim / manifest verification (/verify, POST /api/verify) | Signed-in during private preview | Recompute canonical form + signature + excerpt hash |
| MCP server (9 tools) | Sample mode on any tier / Enterprise+ live (5,000 calls / month on Enterprise) | Every tool payload graded + cited; no ungraded answers |
| REST API v1 | Enterprise+ | Scoped keys; provenance block on every object |
| Webhooks | Enterprise+ | Signed event delivery with retry |
What is roadmap, not live
Single sign-on is not offered on any tier. These are committed directions, not shipped capabilities today: PIV-CAC sign-in, FIPS mode, AWS GovCloud residency, and FedRAMP authorization. The Government tier article and /pricing carry the current status. Treat any claim that these are live as wrong.
For the developer surface, see The REST API v1 and the MCP server. Customers can open the full API and MCP references from inside the app.
Last updated 2026-09-21.
Was this article helpful?
Still need help? If you're signed in, file a ticket with the floating "?" button on any app view. Or email justin@fedgrade.com.