Fda Catalyst Analysis

Methodology inspired by publicly taught biotech catalyst frameworks; all text is an original paraphrase.

Defaults

Preflight

Run canonical pre-flight per contracts/preflight.md. Propagate X-Agentii-Trace per contracts/x-agentii-trace-header.md. Confirm ticker resolution via search_companies before catalyst queries.

Triggers

• "What FDA catalysts are coming up for [ticker]?"
• "When is the PDUFA date for [drug/ticker]?"
• "Build a catalyst calendar for my biotech watchlist."
• "What AdCom meetings are scheduled for [ticker]?"
• "How does the market typically react to [approval/CRL/AdCom vote]?"
• "What are the binary events for [ticker] over the next 6 months?"
• "Which med names have FDA decisions this quarter?"
• "Evaluate the approval odds for [drug] ahead of its PDUFA."
• "What happened the last time a similar drug went to AdCom?"
• "List upcoming device decisions (PMA/De Novo/510(k)) for [ticker]."
• "Which catalysts overlap with [ticker]'s earnings date?"
• "Recap the decision history for [application/drug]."

Production Grounding

• FDA decisions (approve/CRL/withdraw) are the strongest price catalysts in med.medicines_biotech; AdCom votes often pre-move the stock by days.
• Regulatory mechanics: PDUFA target dates, priority review, breakthrough designation, accelerated approval, CRL remediation timelines, AdCom vote patterns (approve/reject/deferral/conditional), post-marketing requirements.
• AdCom-style scrutiny axes to apply when framing outcome odds: safety signals, statistical adequacy, subgroup analyses, missing data, endpoint appropriateness, benefit-risk reasoning (per references/knowledge-frameworks.md).
• Devices: PMA / De Novo / 510(k) decisions carry similar binary-event dynamics (get_device_decision).
• Never fabricate dates, votes, or outcomes. When a tool returns nothing, annotate the coverage gap.

Data Source Priority

1. Structured catalyst data: get_upcoming_pdufa / get_pdufa_decision / get_device_decision (pipeline.fda_calendar_event / device_decision_event).
2. Trial context: search_clinical_trials / get_clinical_trial; approval history: search_fda_approvals / get_fda_approval.
3. Company/filing context: get_company_profile, search_documents, read_source_outline/pages (incl. adcom briefing docs via meeting slugs).
4. Historical grounding: search_investment_cases (sectors=med, event_type=adcom_vote/pdufa_decision/crl/approval), search_by_analogue, search_investment_strategies (sectors=med).
5. Earnings overlap: search_earnings_calendar / list_upcoming_earnings.

Methodology

Retrieval Scope

unstructured_document_search

Retrieval Strategy

1. Resolve ticker(s) via search_companies; collect company_id/cik for device queries.
2. Pull active catalyst events: get_upcoming_pdufa (ticker, horizon_days=default), get_device_decision, upcoming earnings.
3. For each major event, pull decision history (get_pdufa_decision by drug/application) and trial context (search_clinical_trials).
4. For AdCom events, retrieve the meeting documents via list_sources(source_type=adcom_briefing) + read_source_outline/pages using meeting slug citations; apply scrutiny axes.
5. Ground the play in knowledge: search_investment_cases/search_by_analogue with med filters; cite /v/ records.

Temporal Scope

See frontmatter temporal_scope block. Historical decision history may span up to 8 quarters back when requested.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

1. Ticker resolution
2. Catalyst enumeration (dated events)
3. Per-event outcome framing (scrutiny axes + decision history)
4. Historical analogue retrieval
5. Calendar synthesis + risk flags

Modes

• Watchlist (default, multi-ticker): produce one calendar with per-ticker sections; sort by date.
• Single ticker deep-dive: full event timeline + per-event probability framing + positioning context.
• Event type: restrict to PDUFA / AdCom / devices / trials / earnings on request.

Tool Fallbacks

Output File

{ticker}/{YYYY-MM-DD_HHMM}_fda-catalyst-analysis_{affix}.md (watchlist: watchlist/{YYYY-MM-DD_HHMM}_fda-catalyst-calendar_{affix}.md)

Output Structure

1. Executive Summary — highest-impact catalysts in the window, 2-3 sentences
2. Catalyst Calendar — dated table: date, ticker, event type, drug/device, application, expected-impact framing
3. Per-Event Analysis — scrutiny-axes assessment (safety/statistics/subgroups/benefit-risk) + decision history
4. Historical Analogues — matched cases with /v/ citations and quantified outcomes
5. Risk Assessment — binary-risk sizing, overlap clusters, low-verification flags
6. Coverage Gaps — missing data, degraded modes, unverified events

Error Handling

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

• contracts/citation-and-memory.md
• contracts/output-frontmatter-schema.md
• contracts/memory-load.md
• contracts/snapshot-synthesis.md
• contracts/preflight.md
• references/knowledge-frameworks.md