Skip to content
AskFlorence
Main Navigation ArchitectureFlorence AIAgentsMembersAgent PlatformValidationInfrastructure

Appearance

Sidebar Navigation

Overview

Home

Glossary

System Architecture

Consumer & Agent Flow

Florence AI

Overview

Principles

Runtime

Tool surface

Adding a tool

Tool registry

Knowledge: SBC scenarios & CSR

Voice

Evals & observability

Provider risk & portability

Outage playbook

Roadmap

Build plan

Agents

Overview

Workflows & pain points

Members

Overview

Medicaid coverage gap

Carriers

Overview

Marketplaces

Overview

Agency

Overview

Regulations

Overview

Agent Platform

Overview

Auth Architecture

MongoDB Permissioning

Compliance Model

Data Models

Data Sources

Overview

CMS Marketplace API

CMS dependency map

PUF Data

State Subsidies

SBE Ingestion Playbook

SBE State Watchouts + Decisions

CA Phase C/D Playbook

NY Phase C/D Playbook

Validation

Overview

Methodology

APTC Formula

California 2026

New York 2026

CAPS Formula

Scenario Results

Infrastructure

Account Inventory

AWS Setup Runbook

AWS Organizations

CloudTrail

GuardDuty

Security Hub

Config

CloudFront + WAFv2

Data sources & ingest

Phase 4 DNS

Change Log

Vulnerability Management

MongoDB Setup

Access Control

Data Classification

Documentation Hosting

Post-deploy Smoke

Development

Preflight (local CI mirror)

Testing strategy

Compliance

Overview (auditor entry point)

SOC 2 Control Mapping

HIPAA Control Mapping

CMS EDE Appendix A Mapping

Risk Assessment

Encryption Policy

Data Retention Policy

Privacy Impact Assessment

Consent Capture & Versioning

Incident Response Plan

Access Control Policy

Marketing vs. Portal Analytics

Vendor / Subprocessor Register

Dependency Vulnerability Policy

BAA / Compliance Evidence

Compliance-Automation Integration

Compliance-Automation Vendor Evaluation

Penetration Test Reports

Architecture

Portal entry handoff

Mobile app strategy

Deferred architecture decisions

Session cookie architecture

Share flows

Decisions (ADRs)

Index

0001 — Atlas project isolation

0002 — Append-only audit log

0003 — Narrow-scoped Mongo users

0004 — Cross-cluster Atlas PrivateLink

0005 — Delayed-job architecture

0006 — Mongo user simplification

0007 — Terraform owns ECS task def

0008 — E2E testing strategy

0009 — Self-hosted analytics + observability (superseded)

0010 — PostHog HIPAA Cloud (supersedes 0009)

Runbooks

Security Incident Response

Break-Glass Root Login

Onboard Team Member

Offboard Team Member

Atlas user provisioning

Deploy via Terraform (ENG-277)

Rollback via Terraform (ENG-277)

S3 data bucket migration (planned Phase 11)

Access Reviews

2026-Q2 Review

Session log

Index

2026-04-23 — Phase 10 DNS cutover

2026-04-22 — Phase 8 prod AWS mirror

2026-04-22 — Phase 7 Atlas VPC peering

2026-04-22 — Phase 6 CloudFront + WAF

2026-04-21 — Phase 5 staging go-live

2026-04-17 — Atlas staging

Briefs

Index

Member portal plan (ENG-187)

2026-04-16/17 handoff

2026-04-17 Atlas handoff

System briefing (2026-04-17)

Creative AdBundance proposal brief

Creative AdBundance analytics brief

ElevenLabs RN integration research

Policies

Overview

On this page

Briefs ​

Input and handoff documents that fed a specific session of agent-executed work against this repo. They are preserved for historical reference, not as living documents.

What goes here ​

  • Session handoffs (SESSION_BRIEF_*.md). Written at the end of a session to brief the next session — either a sibling parallel session running against the same repo, or the same agent picking up after a context gap. Short, scoped, often name state that was left behind (account IDs, resource ARNs, outstanding items).
  • Build briefs (BRIEF_*.md). Written by a human before a session to tell the agent what to build, why, and under what constraints. The output of those sessions landed in tracked code + docs; the brief is kept alongside as the input-of-record.
  • System briefings (*_BRIEFING.md). Point-in-time snapshots of the system as it existed at that date. Useful for diffing "how did the system look then vs. now" when an auditor or future contributor asks.

What does NOT go here ​

  • Long-form session records. Those go in docs/session-log/. The distinction is audience and shape:
    • A brief is short, pragmatic, and consumed once.
    • A session log is long, narrative, and read later for audit evidence.
  • Change records of infrastructure. Those go in docs/infrastructure/change-log.md.
  • Secrets or credentials. Never in any file under this directory. A brief can name a secret (e.g. "MONGODB_URI_WAITLIST_WRITE") but never its value.

Naming ​

  • SESSION_BRIEF_<YYYY-MM-DD>[_topic].md
  • BRIEF_<SHORT_TOPIC>.md
  • <TOPIC>_BRIEFING.md

Existing files predate strict naming and are kept as-is for link stability.

Index ​

  • SESSION_BRIEF_2026-04-16_17.md — handoff across the 2026-04-16 / 17 session boundary.
  • SESSION_BRIEF_2026-04-17_atlas.md — Atlas-session handoff to AWS migration session (precedent for the 2026-04-17-atlas-staging session log).
  • ASKFLORENCE_SYSTEM_BRIEFING.md — 2026-04-17 point-in-time system briefing, v0.3.2.
  • BRIEF_CA_PROPOSAL.md — input brief for building /creative-adbundance/proposal, consumed in v0.16.0.
  • creative-adbundance-analytics-brief.md — partner-facing handoff explaining the user flow, the auth-wall cut between marketing and portal, and the per-tool compliance review loop. Authored 2026-05-11 for ENG-280. Companion to the internal Marketing vs. Portal Analytics control doc.
  • BRIEF_FLORENCE_AI_ARCHITECTURE.md — 2026-04-22 input brief framing the Florence AI architecture + infrastructure research track. Not finalized architecture; authoritative decisions live on the Florence AI architecture parent GitHub issue.
  • doctor-rx-session-prompt.md — input prompt for the parallel doctor-rx worktree (research-first; consumed by the worktree's session brief).
  • plans-redesign-brief.md — input brief for the /plans page redesign worktree (Wave 1 shipped in v0.36.0).
  • SESSION_PROMPT_2026-05-01_tier-0-5-federal.md — input prompt for the Tier 0.5 federal+NY ZIP USPS-completeness audit + apply session (#80). Outcome header at top; full reports in docs/validation/tier-0-5-federal-uspscompleteness.md + audit-operations-runbook.md.
Pager
Previous page2026-04-17 — Atlas staging
Next pageMember portal plan (ENG-187)

AskFlorence Internal Documentation. Not for public distribution.

AskFlorence

Internal Documentation

Access restricted. Not for public distribution.