Blog · Page 16
Field notes.
Page 16 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
Security-questionnaire volume in 2025, the data
Safe Security's 500+/year claim, tested against the volume we see across our own fleet. Category breakdowns, seasonal spikes, and the questions that are growing fastest.
Color-team review: the full playbook
The operational companion to our color-team essay. Step-by-step procedures for pink, red, gold, and white teams — when to run each, who attends, the rubrics they apply, and the templates that make the discipline portable.
The Halloween submit weekend triage
Operational note for proposal teams facing weekend deadlines. Three rules we run on every weekend submit. Short, written down so we can find it again next Halloween.
The DDQ evidence-attachment API
How buyer-side evidence-request fields get auto-populated from a KB evidence vault. The schema, the matching logic, and the human-in-the-loop step we will not remove.
The five compliance-matrix mistakes that lose bids
Real patterns from real debriefs. The matrix mistakes that surface as scoring penalties on the buyer side, and the discipline that prevents each one. Citations to VisibleThread on the most common cause.
Per-customer embedding tenancy, explained
How tenant isolation works at the vector level in PursuitAgent. Why we use Postgres row-level security on pgvector as the default, where shared embedding spaces would be cheaper, and the trade-offs we are not willing to take.
The federal Q1 push: triaging three RFPs at once
The 90-minute drill we use when three federal solicitations drop in the same day. Three buckets, four questions per bid, one written decision. The thing you cannot afford to do on a Friday afternoon in October.
Anatomy of a multi-award IDIQ solicitation
Reading a federal multi-award IDIQ end-to-end. Task orders, ceiling prices, evaluation factors, and three red flags to catch before bid/no-bid. Annotated walk-through of a recent civilian-agency vehicle.
Shipped: bulk edit for answer blocks, with undo
A real-world request we dragged our feet on for nine months. Bulk edit is now in the product, with version-aware undo and a confirmation flow that prevents the silent overwrite that made us nervous in the first place.
The Q4 DDQ surge is almost here
Procurement-side patterns for Q4 2025: what buyers are sending right now, what volume looks like at the question level, and what to expect in the next eight weeks.
Citation UI: three designs we tried, two we kept
How we render inline citations next to grounded-AI output. Three UX experiments — footnote chips, side-pane evidence cards, and inline hover popovers — and what we learned about which ones reviewers actually use.
Discriminator tests: three worked examples
The APMP discriminator test is simple to state and brutal to apply. Three real-shape proposal sections, run through the discriminator filter, with the rewrites that survive.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.