Blog · Page 17

Field notes.

Page 17 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.

Engineering

KB block versioning: the five-year commit history

How a KB block evolves across 18 proposals, three approvals, and one rollback. The data model behind block versioning, why we keep every prior version, and the queries that make it useful.

The PursuitAgent engineering team
Category

Six months of the blog: what readers keep coming back to

Six months in, three posts keep getting shared, two flopped, and one surprised me. Notes from the founder on what the field-journal experiment is teaching us about what proposal practitioners actually want to read.

Bo Bergstrom
Research Feature

Loopio at ten: what a decade of reviews tells us

Reading 10 years of public Loopio reviews end-to-end. The trajectory of buyer sentiment from 2016 to 2025, what the product fixed, what it never did, and what the trajectory predicts for incumbent RFP tools generally.

The PursuitAgent research team
Team & Workflow

The Saturday backlog triage pattern

Thirty minutes on a Saturday morning, three buckets, and Monday is ready to go. A small operational ritual we use to keep the proposal backlog from compounding into chaos.

PursuitAgent
Category

Grounded AI is not a feature, it's a refusal

Opinion. The thing that makes grounded AI different from regular AI is what the system refuses to do — answer when retrieval is empty. Here's what we will not ship even when reviewers ask for it.

Bo Bergstrom
Team & Workflow Long read

SME collaboration, reconsidered

The 48% bottleneck hasn't moved in five years. Every playbook that attacks it via better communication has failed. The economic frame, three patterns that partially work, the one that fully works, what tooling must do.

Sarah Smith
Team & Workflow

SME collaboration, reconsidered: the preview

The async-first SME workflow we wrote about all year was half-right. Two hundred real interviews and a year of customer data later, here is what we got right, what we got wrong, and what the canonical post tomorrow will argue.

Sarah Smith
Engineering

The background job queue for proposal processing

How Hatchet orchestrates the ingest, classify, draft, and verify stages of a proposal response. The four stages, the retry policies, the dead-letter handling, and the one place we deliberately chose synchronous over async.

The PursuitAgent engineering team
RFP Mechanics

Compliance-matrix tooling, a quick bake-off

Four tools, one 60-page state RFP, the same compliance matrix task. Time-to-matrix and accuracy against a hand-built reference. The results were closer than I expected and the failure modes were different than I expected.

PursuitAgent
Research Feature

Healthcare RFP compliance patterns

An analysis of HIPAA, HITRUST, and data-residency clauses across 50 hospital-system RFPs. What language is now standard, what is still customer-specific, and the three clauses that have sharpened since 2024.

The PursuitAgent research team
RFP Mechanics

The amendment checklist every proposal manager should run

An RFP amendment lands. Six questions to answer before you click 'acknowledge receipt.' Each one has bitten a team I know in the last 18 months.

PursuitAgent
Craft

Three exec summaries I rewrote this week, part 6

The October installment of the rewrite series. A SaaS bid, a federal IT services bid, and a healthcare DDQ-fronted RFP. Three before-and-afters and what each rewrite was actually doing.

Sarah Smith

Prefer to see the product?

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