- market_intel_orchestrator.py: Updated generate_outreach_campaign to identify all relevant roles, generate top 5, and return remaining as suggestions. Added specific_role mode.
- types.ts: Added OutreachResponse interface.
- geminiService.ts: Updated to handle new response structure and specificRole parameter.
- StepOutreach.tsx: Added sidebar section for Suggested Roles with on-demand generation buttons.
- market_intel_orchestrator.py: Updated analyze_company to NOT abort if homepage scraping fails (e.g. 403 Forbidden). Instead, it sets a placeholder and proceeds using external search signals.
- market_intel_orchestrator.py: Updated get_website_text to use a modern, realistic User-Agent to reduce blocking.
- market_intel_orchestrator.py: Adjusted Gemini prompt to handle missing homepage content gracefully.
- market_intel_orchestrator.py: Rewrote prompt in generate_search_strategy to explicitly distinguish between 'Your Company (Context)' and 'Reference Client (Seed)'. This fixes the issue where the AI was searching for competitors to the user's company instead of the reference client.
- market_intel_orchestrator.py: Clarified prompt in identify_competitors.
- market_intel_orchestrator.py: Added RAW JSON debug logging to stderr to diagnose missing fields.
- Added searchStrategyICP, digitalSignals, and targetPages to the JSON output in market_intel_orchestrator.py.
- Updated the prompt and fallback error handling to include the new fields.
- Implementierung der rollenbasierten Campaign-Engine mit operativem Fokus (Grit).
- Integration von Social Proof (Referenzkunden) in die E-Mail-Generierung.
- Erweiterung des Deep Tech Audits um gezielte Wettbewerber-Recherche (Technographic Search).
- Fix des Lösch-Bugs in der Target-Liste und Optimierung des Frontend-States.
- Erweiterung des Markdown-Exports um transparente Proof-Links und Evidenz.
- Aktualisierung der Dokumentation in readme.md und market_intel_backend_plan.md.
- Integrated ICP-based lookalike sourcing.
- Implemented Deep Tech Audit with automated evidence collection.
- Enhanced processing terminal with real-time logs.
- Refined daily logging and resolved all dependency issues.
- Documented final status and next steps.
- Updated readme.md with new step 3 audit details.
- Updated market_intel_backend_plan.md with current status and achievements.
- Fixed SerpAPI key file path in orchestrator.
- Documented the transition to direct REST API calls and enhanced terminal UX.
- Added to parse industries from Markdown.
- Added to find local/national/international lookalikes.
- Added for deep tech audit (website search, scraping, AI analysis).
- Updated prompt engineering for better results grounding.
- Refactored market_intel_orchestrator.py for direct Gemini API (v1) calls.\n- Updated model to gemini-2.5-pro for enhanced capabilities.\n- Implemented minimal stdout logging for improved traceability within Docker.\n- Optimized Dockerfile and introduced market-intel.requirements.txt for leaner, faster builds.\n- Ensured end-to-end communication from React frontend through Node.js bridge to Python backend is fully functional.
