Market Analyst

Reshape market-analyst into a design tool first — the source of truth for Qpoint's problem space — by adding a micro-problem layer (use case → micro problem → observations) on top of the existing market lens, with a curated registry, extraction-proposed candidates, computed standing, product surfaces, document intake, and briefs/stories that cite problems.

Declare the nature of each conversation at triage (source type × call type), tag every observation with the speaker's perspective (first-hand / relayed / internal), enforce evidence ceilings and a code-computed validation gate, extract session records (decisions / todos / ideas) from working sessions, and formalize the conversations → insights → brief hand-off into the design machine.

Modernize Claude API usage across the pipeline, evaluate and finalize data-architecture decision, reshape cross-call analysis for use-case honing.

Clean up project documentation for sharing with team members

Reorient pipeline and app around AI-agent-security pivot: archive phase 1, use-case-centric extraction, multi-source feedback, architecture debt paydown.

Explore and integrate Avoma notes data into extraction pipeline and dashboard visualizations.

Integrate Sagetap call transcripts into the extraction pipeline alongside Avoma.

Build an interactive analysis agent as a Claude Code skill for ad-hoc querying of call data.

Refine how extracted data is displayed in the dashboard and improve extraction quality where gaps exist.

Add Google OAuth to restrict dashboard access to @qpoint.io team members.

Establish a modular, reusable brand styling foundation and update the market analysis dashboard's visual identity.

Build the data extraction pipeline — ingesting call transcripts from multiple sources and extracting structured insights via Claude.