Insights · Notes from the field
Essays on evals, compliance posture, postmortem culture, and the operational craft of zero-to-PMF engagements.
Featured · Compliance
Chunking, redaction, retrieval filters, and eval hooks so regulated AI answers without stuffing patient data into every context window.
Compliance
Practical notice, purpose limitation, and consent patterns for AI products selling to Indian regulated buyers — without freezing the roadmap.
Compliance
A decision tree for LLM vendors, subprocessors, and when synthetic data is enough — before anyone pastes real patient data into a prompt.
Compliance
Shared primitives for regulated AI — access control, logs, minimization — and the jurisdiction-specific deltas US and Indian buyers actually diligence.
Compliance
BAA availability, retention defaults, region options, and eval portability — how Brandlabs shortlists model providers for healthcare and regulated buyers.
Compliance
What to log for HIPAA-aware LLM systems, what never to log, how long to keep it, and who can open the trail.
Evals
How to evaluate refusal, escalation, medical-advice boundaries, and hallucinated dosages — before a health assistant meets real users.
Evals
Golden sets, adversarial sets, and ownership so your LLM suite still means something after six months of prompt thrash.
Evals
The Brandlabs Discovery Sprint pattern for setting LLM eval targets in weeks 1–3 — before feature thrash eats the timeline.
Evals
Sampling, cost caps, flake handling, and which LLM eval suites must stay required vs nightly — so production cannot silently regress.
Delivery
FDE, senior engineers, product design, and compliance-as-needed — roles and anti-patterns for shipping regulated AI in 12–20 weeks.
Sector
Diligence questions on BAA fluency, eval discipline, and clinical workflow empathy — before you hire a studio to ship your AI product.
Delivery
Inputs, outputs, kill criteria, and how Brandlabs maps a Discovery Sprint into a 12–20 week zero-to-PMF engagement.
Sector
Questions CFOs and compliance officers should ask before signing an AI vendor — DPDP, updates, liability, and evidence — not just a demo.
Delivery
Foundation → build to alpha → production-harden → PMF hunt — with eval and compliance gates at each phase.
Sector
Privacy, language, and stigma-aware product patterns from shipping telehealth for women’s health — so care feels safe enough to start.
Sector
Escalation, localization, and content safety patterns for healthcare chat on WhatsApp — from shipping Myna Bolo in production.
Sector
Latency, vernacular STT/TTS, and when voice beats chat — lessons from rebuilding Myna Voice AI for rural women’s health support.
Sector
Productizing 69,000+ obligations and regulations that change ~15 times a day — without turning an AI assistant into unauthorized legal advice.
Evals
Why we treat the eval suite as a first-class deliverable — and how it changes how we negotiate scope.
Delivery
A pattern for weekly demos that are evidence, not theatre. What we ship, what we don't, and what we say out loud.
Compliance
HIPAA and DPDP shouldn't be a last-mile checklist. Here's how we bake them into the first commit.
Evals
The cultural and technical loop that turns production incidents into permanent guardrails.
Delivery
Not a project manager, not a consultant. A senior engineer who lives in your Slack and writes the hardest code.