Blog · Page 24

Field notes.

Page 24 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.

Engineering

The cost per response, broken down to the penny

Embedding calls, retrieval compute, draft tokens, verifier tokens, storage. The unit cost structure of a single drafted RFP answer, with a worked example. We publish the unit economics, not customer costs.

The PursuitAgent engineering team
Category

Pricing in public, ninety days in

We posted real prices on the marketing site at launch. Ninety days later, here is what changed about the sales conversations, what surprised us, and what is still uncomfortable about it.

Bo Bergstrom
RFP Mechanics

Anatomy of a 112-page DoD RFP

A composite walkthrough of a 112-page Department of Defense solicitation — section structure, scoring methodology, evaluation factors, where the editorial weight actually sits. Drawn from public DoD RFP patterns on SAM.gov.

The PursuitAgent research team
Procurement

The DDQ answer-reuse myth

The pitch is: every DDQ is mostly the same, so reuse the answers. The reality is: every DDQ is mostly similar but just different enough that naive reuse fails. The gap between similar and identical is where the work lives.

PursuitAgent
Engineering

Shipped: win/loss pair capture at submit time

When a proposal hits submit, PursuitAgent now captures the response, the disposition, and the structured post-mortem inputs into a single record. The first piece of the win/loss intelligence loop is in production.

PursuitAgent
RFP Mechanics Long read

Reading an RFP like the procurement lead who wrote it

RFPs are procurement documents written by named humans with known constraints, drafted from templates reused for fifteen bids. Read them that way and the response writes itself differently. The canonical long version.

Sarah Smith
Procurement

Ingesting a 300-question security questionnaire

A 300-question security questionnaire is a throughput problem, not a writing problem. The ingest pipeline has five stages: extract, classify, dedupe against the last one, retrieve, assemble. Here is what each one does and where it costs.

The PursuitAgent engineering team
Engineering

Query rewriting for RFP questions with implicit context

Most RFP questions retrieve poorly because they assume context the corpus does not carry. Query rewriting turns 'describe your approach' into a retrieval string that hits. Examples, the rewrite chain, and the cost tradeoff.

The PursuitAgent engineering team
Team & Workflow

Stop CC-ing your SMEs, part 2

Six weeks after we said stop CC-ing your SMEs on every email, here are the patterns that have actually shown up in disciplined teams. The replacement was not a tool — it was a queue.

PursuitAgent
Research Feature

Win rates by RFP format: government, commercial, DDQ

Public data on win rates is sparse and inconsistent. Here's what the GAO bid-protest record, APMP benchmarks, and vendor-published numbers actually let you say — and where the data gaps are big enough to matter.

The PursuitAgent research team
RFP Mechanics

The Sunday night compliance check

A 15-minute habit before Monday's kickoff. Read the compliance matrix against the calendar. Find the four things that will hurt you in week three. Write the email Sunday night so Monday is not the day you discover them.

PursuitAgent
Craft

Three exec summaries I rewrote this week, part 3

Field notes from the editing desk. Three illustrative before-and-afters of executive summary openings I cut down this week, and the pattern each one is fighting.

Sarah Smith

Prefer to see the product?

Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.