Sep 28, 2026 • 5 min read
AI Features Need Unit Economics
The useful cost of an AI feature includes retries, retrieval, review, and support—not just the price of one successful model response.
AIProductOperations
Dev Blog
Building systems that survive real use.
Essays on HubSpot architecture, AI workflow design, and engineering delivery for teams that care about what happens after launch, when operators, edge cases, and changing requirements put the real system on display.
Explore the blog
Find your next read.
13 articles in AI
Clear filtersAug 4, 2026 • 5 min read
Desktop AI Needs a Hardware Budget
A useful desktop AI product treats memory, model formats, fallbacks, and degraded states as product decisions—not surprises for the person using it.
AIDesktopPerformance
Aug 1, 2026 • 6 min read
AI Evaluations Are Product Requirements
If an AI feature can change a customer decision, an operator workflow, or a safety boundary, its evaluation plan is part of the product requirement.
AIProductDelivery
Jul 1, 2026 • 3 min read
The Model Is Only One Part of the Interface
AI product quality depends on the full interface around the model: inputs, controls, evidence, state, review paths, and recovery behavior.
AIProductSystems
Jun 28, 2026 • 2 min read
Good AI Tools Preserve the Decision Trail
AI tools are easier to trust and improve when they preserve inputs, evidence, decisions, approvals, and corrections instead of only storing the final output.
AIGovernanceOperations
Jun 22, 2026 • 3 min read
When AI Should Ask Before Acting
The best AI workflows know when to pause for clarification, approval, or missing context instead of forcing a confident action from uncertain inputs.
AIOperationsProduct
Jun 19, 2026 • 3 min read
Retrieval Quality Is Product Quality
Retrieval is not plumbing in an AI product. It directly shapes whether the answer feels relevant, grounded, current, and useful.
AIDataArchitecture
Jun 14, 2026 • 3 min read
AI Agents Need Operating Boundaries
AI agents become more useful when their authority, inputs, tools, and escalation paths are defined before they start acting inside real workflows.
AIAutomationGovernance
Jun 4, 2026 • 5 min read
Prompt Changes Are Production Changes
Prompt edits can change routing, escalation, and decision quality in production, so they deserve versioning, evaluation, and rollback.
AIDeliveryOperations
Jun 1, 2026 • 6 min read
Documentation Is Part of the AI Stack
AI systems get more reliable when documentation defines the terms, states, tool behavior, and exception handling the workflow depends on.
AIDocumentationSystems
May 26, 2026 • 8 min read
Most AI Product Problems Are Context Problems
AI features improve when teams treat context assembly as product and systems design work instead of assuming the model can infer its way past noisy, stale, or incomplete inputs.
AISystemsArchitecture
May 10, 2026 • 5 min read
AI Workflows That Survive Contact With Reality
Durable AI systems win by structuring decisions, preserving evidence, and designing the workflow around the model for operators.
AIAutomationSystems
May 8, 2026 • 4 min read
Automation Needs a Human Exit Ramp
Good automation removes routine work but still gives people a clear, informed way to take over exceptions.
AutomationAIOperations