Blog · Page 21

Field notes.

Page 21 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.

Craft

Preview: the field guide to win themes that actually win

A teaser for tomorrow's win-themes pillar. Two worked examples — one theme that fails the swap-name test, one that survives it — and what the difference looks like in the response.

Sarah Smith
Engineering

The SME Slack bot: architecture and boundaries

How the PursuitAgent SME bot asks for input, what it does with the answer, and what it deliberately refuses to do. A short tour of the boundary between the bot and the human.

The PursuitAgent engineering team
Research Long read

State of Proposal Tools — Wave 1 2025

The annual benchmark. What customers say about the incumbents and the challengers, what's true in pricing, where the AI moment lands honestly, and what changes in 2025.

The PursuitAgent research team
Procurement

The DDQ review cycle you can actually finish

Two rounds, not four. The structure that keeps security questionnaires from missing deadlines, and what to drop when you cut the ceremony.

Sarah Smith
Team & Workflow

The Saturday shuffle: reprioritizing the proposal queue

A 10-minute weekly ritual that reprices every active proposal against its actual deadline pressure and probability of win.

PursuitAgent
RFP Mechanics

Amendments are the real RFP

Why the third amendment usually contains the evaluation criterion that decides the bid, and what it means for how teams structure intake.

PursuitAgent
Engineering

KB schema evolution, year one

Four migrations we ran on the knowledge-base blocks table, three we rolled back, and what the schema looks like now. A field report on schema discipline.

The PursuitAgent engineering team
Craft

Section openings that earn the next paragraph

Six real section openings from winning proposals, annotated. What they did, why the evaluator kept reading, and how to write them yourself.

Sarah Smith
Engineering

Retrieval evaluation, part 2: dealing with numeric claims

Why numeric facts break vanilla retrieval and the two tactics — hybrid search and numeric-claim isolation — that fix it. Continuation of the eval series.

The PursuitAgent engineering team
Category

The word 'intelligence' and what it had better mean

Why PursuitAgent calls itself proposal intelligence and what the word obligates us to. A short post about a long word.

Bo Bergstrom
Research Feature

What a Magic Quadrant for proposal management would need to evaluate

There is no Gartner Magic Quadrant for proposal-management software. What a hypothetical MQ would need to measure — where the framework translates, where it would have to add new axes for grounded AI.

The PursuitAgent research team
Procurement

The Friday DDQ batch we process in under an hour

What automation does to a weekly batch of security questionnaires, and the four things it still can't do.

PursuitAgent

Prefer to see the product?

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