cf0 ships in steady, dated releases. Each entry below is a real shipment customers were notified about. For platform announcements, follow @cf0ai. For early-access programs and the founding-analyst circle, contact [email protected].Documentation Index
Fetch the complete documentation index at: https://docs.cf0.ai/llms.txt
Use this file to discover all available pages before exploring further.
What’s new
- Excel and PowerPoint output — cf0 produces Excel and PowerPoint files integrated with any analysis you run, or with documents you upload.
- Coverage page — configure custom news sources per company, sector, or theme. The agent uses your chosen sources for monitoring and report context.
- Fund filings — N-PORT, N-CSR, and N-PX added. Go deeper on institutional holdings and fund-level disclosures.
- Autonomous agents (beta) — as you analyse companies, cf0 drafts overnight briefs on those names and on the news so the analysis is ready when you start your morning.
What’s new
- Org dashboard — admins see how the team is using cf0: who’s active, which skills they use, who might need help getting started. Aggregate counts only — thread bodies stay private to the analyst.
- Team document sharing — upload a model or research file and it appears in every analyst’s workspace. Analysts can request shares; admins approve with one click.
- Shared documents power the AI — anything your team shares becomes part of cf0’s knowledge. Ask about a shared doc and the agent knows where to find it.
- Report version history — scrub through every version of an edited report; restore any prior state.
- All uploaded documents are editable — same workflow as report editing, applied to PDFs and Word docs.
What’s new
- Report editing v1 — natural-language edits to generated reports with inline diff review and accept/reject controls.
/compactslash command — manually trigger chat compaction to keep context focused on what matters.- Interrupt button — safely stop the agent after sending a message, without losing your place in the chat.
- Unified document editing — extends the report-edit pipeline to any uploaded document (PDF, DOCX, TXT, MD, HTML). Upload, ask for edits, review changes as inline diffs.
What’s new
- Per-chat artifacts — every chat stores its reports, audits, and long-action workflows. Render them in the artifact panel via preview mode or PDF mode.
- Side-by-side report editing — after generating a report, open the chat and use the artifacts dropdown in the sidebar.
@the file and ask for edits; changes appear inline so you can accept or decline section-by-section. - Frontend stability pass — fewer transient UI errors on long sessions and mid-stream refreshes.
- Richer LLM output — better visualization of tables, sources, and structured data inline in chat.
What’s new
- Interactive observability panel — deep visibility into what the LLM is actually reading from filings, financials, and sources, not just the tools it’s calling.
- Clarifying-question gates — the model now pauses to ask for the assumptions that change outputs significantly (WACC, growth rates, terminal multiples) before producing a DCF or valuation.
- Filings ingestion page — view 10-K, 10-Q, 8-K, 13-F, and S-1 filings, and ingest them on demand for new companies.
- Longer chat context — conversations no longer die out via early compaction; long research threads stay coherent.
- Speed and accuracy across queries — broad performance pass on the chat and report paths.
What’s new
- Global equities — coverage now extends to public equities outside the US.
- Faster queries — overall response time improved on chat and report generation.
- Smarter intelligence — better reasoning on multi-step questions; fewer drop-offs mid-answer.
- Accuracy improvements — tighter grounding to source documents reduces wrong figures on long conversations.
- Quieter deploys — code updates can now ship without interrupting in-flight chat sessions.
What’s new
- Calculation accuracy — fewer wrong numbers, fewer hallucinated figures, better cross-checking against source filings.
- SEC data speed — filings load and stream noticeably faster across 10-K, 10-Q, and 8-K queries.
- UI smoothness — chat ordering fixes (FIFO tool-event pairing) so streamed thinking and tool calls render in true chronological order.
- Document upload — drag-drop documents directly into Lab; sidebar shows uploaded files per chat.
- Infrastructure stability — six tracks of infra gap closure landed together (auth, sandbox lifecycle, S3 reconciliation, deploy hooks).