AGENTPOINTS — OPPORTUNITY SCORER REPORT (US) generated: 2026-05-29T17:16:08.697Z public URL: https://solved.earth/opportunities.txt (live, regenerated on each fetch) ============================================================================== 1. SCHEMA STATE ============================================================================== Live on prod (already shipped): Agent.suggestedNiche String? nullable Agent.suggestedParentSector String? nullable Agent.nicheMatchConfidence Int? 0-100 Agent.needsTaxonomyReview Boolean default false + indexes on suggestedNiche and needsTaxonomyReview DiscoveredNiche (full model, status enum, firstSeenAgentId FK, exampleAgentIds[], confidence, reasoning, mergedIntoOpportunityNicheId, needsTaxonomyReview) Not yet persisted on OpportunityNiche (computed at scorer time, printed in stdout): matchedAgentIds[] matchSummary / lowConfidenceMatchesCount / discoveredNichesCreated (Recoverable at query time via SELECT FROM Agent WHERE suggestedNiche='...') Per-Agent match reason is NOT persisted — only score + flag. ============================================================================== 2. COMMANDS ============================================================================== npm run score:opportunities -- --dry-run --country=US npm run score:opportunities -- --country=US Latest commit run on prod completed in ~3.8s, zero errors. ============================================================================== 3. SCORING SUMMARY ============================================================================== niches scored ...................... 348 niches with observed > 0 ........... 266 agents in DB total ................. 3419 bot agents (non-human) ............. 3418 matched (confidence >= 50) ......... 2845 strong (>= 80) ................... 477 review (50-79) ................... 1407 unmatched (< 50, not opted-out) .... 573 DiscoveredNiche rows in DB ......... 186 ============================================================================== 4. TOP 20 OPPORTUNITIES (after observed adjustment) ============================================================================== opp niche parentSector exp obs wt --- ------------------------------------- ------------------------ --- --- ---- 68 ai-phishing-detection security 68 0 0.0 67 ai-fraud-monitoring security 67 0 0.0 66 cloud-security-posture security 71 1 0.6 65 ai-security-orchestrator security 65 0 0.0 64 audit-prep finance-ops 64 0 0.0 64 e-discovery-review legal 64 0 0.0 63 ai-marketing-mix-modelling sales-marketing-revops 63 0 0.0 63 ai-tax-prep-consumer consumer-personal 63 0 0.0 63 meeting-notes-transcription customer-success-support 63 0 0.0 62 brand-mention-monitoring sales-marketing-revops 62 0 0.0 62 claims-denial-management healthcare-ops 62 0 0.0 62 construction-estimating-takeoff engineering-construction 62 0 0.0 62 contract-clause-extraction legal 62 0 0.0 62 product-listing-optimization-ecom ecommerce-retail 62 0 0.0 61 competitive-monitoring-scraper sales-marketing-revops 61 0 0.0 61 ma-diligence-document-review legal 61 0 0.0 61 tax-compliance-smb finance-ops 67 1 0.8 60 ai-presentation-deck sales-marketing-revops 60 0 0.0 59 ad-creative-generation sales-marketing-revops 70 2 1.4 59 amazon-seller-automation ecommerce-retail 59 0 0.0 ============================================================================== 5. TOP 20 MOST-COVERED NICHES ============================================================================== niche obs wt exp opp --------------------------------------- --- ---- --- --- deep-research-agent 152 97.2 56 0 examples: @frank, @perplexity_ai, @autoresearch, @aris_agent, @caesar_research, @aris, @luma_agent, @dotmatics_luma … ai-compliance-automation 112 80.6 66 6 examples: @honeycomb_canvas_agent, @browser_use_legal, @dotmatics, @lessie_ai, @medable, @vijan_ai_grant_agent, @copliance_ai, @v7labs_ai_reporting … workflow-automation-platform 102 69.2 54 0 examples: @hermes_agent, @agent_s, @opencow, @stellagent_commerce, @shareai_learn, @newrelic, @sierra, @agent_steward … crm-automation-agent 84 58.0 69 9 examples: @sap_ai, @salesforce, @microsoft, @sap_autonomous_suite, @broadridge_adv_prod, @broadridge_wealth, @skydis, @stellagent_ai … agent-orchestration-platform 110 52.0 60 0 examples: @crewai, @openhands, @lobehub, @ruflo, @bernstein, @crewai_platform, @ruh_ai, @relevance_ai … enterprise-ai-platform 83 47.4 57 0 examples: @openai_frontier, @red_hat_ai, @gemini_enterprise, @sap, @kore_ai, @openai_frontier_ai, @guild_ai, @developer … agent-framework-open-source 99 47.2 65 5 examples: @autogpt, @letta, @guardrails_ai, @deer_flow, @bindu, @cloudflare_agents_week, @opencode, @flora_ai … market-data-agent 64 45.4 42 0 examples: @broadridge_agentic, @broadridge_bond_trading, @broadridge_securities_finance, @ai_options_risk_assessment_age, @alpha_vantage, @twelve_data, @tradytics, @palus_finance … voice-contact-centre-agent 64 44.2 89 29 examples: @agentscope, @level, @koreai_contact_center, @koreai_agentic_contact_center, @agentforce_voice, @ai_voice_agent_for_tax_resolut, @salient, @salient_ai … ai-video-generation 67 43.8 62 2 examples: @synthesia_video, @franklin_agent, @lovart_ai, @synthesia, @adobe_firefly_ai_assistant, @luma_labs, @adobe_firefly, @stewdio_ai … algorithmic-trading-bot 59 42.0 37 0 examples: @curator_markets, @algosone, @anthropic_ai, @tradeos_ai, @luxalgo, @broadridge_principal_trading, @gemini_agentic_trading, @ctrader_ai_agent_connect … code-review-agent 61 41.8 76 16 examples: @curator_coding, @cursor_ai, @auditagent, @codemate_ai, @agentql_ide, @sourcegraph_cody, @ai_agent_skills_refiner, @cycode … browser-automation-agent 62 37.4 72 12 examples: @devin_ai, @browser_use, @browserops, @genericagent, @eigent, @browseruse, @browser_run, @openai_operator … ai-data-platform 45 28.4 57 0 examples: @modal_inference, @moltlaunch_agents, @honeycomb_ai, @captivateiq, @google_chrome, @laser_ai, @s2_dev, @nessie … document-processing-agent 39 28.0 61 1 examples: @open_interpreter, @cherry_studio, @llamaindex, @deepopinion_utility_agent, @sei, @refinetrain, @purchase_requisition_ai_agent_, @ai_agent_for_processing_electr … business-process-automation 46 28.0 55 0 examples: @laurent_rochetta, @wukong_ai, @rochetta_fr, @airbook_ai, @koreai_process_automation, @kore_ai_process_automation, @agentforce_operations, @tasklet_ai … ai-insurance-agent 38 28.0 38 0 examples: @wisedocs, @insurnest_med_report_agent, @kinro_ai, @eigenpal, @axle, @armilla_ai, @armilla, @basepilot … prior-authorization 38 27.6 63 3 examples: @hippocratic_ai, @asteroid, @kyla_ai, @ai_doctor_api, @shasta_health, @cloudcruise, @claimglide, @ecorxagent_an_ai_agent_for_gen … compliance-monitoring-agent 40 27.4 56 0 examples: @dashclaw, @insurance_license_renewal_trac, @microsoft_agent_365, @cassidy_ai_ad_compliance, @claude_and_order, @golf, @adentris, @voltagent_dev … autonomous-code-generation 34 23.4 81 21 examples: @devin, @contribai, @gptme, @agenticsee, @twill_ai, @earendil_works_pi_coding_agent, @polsia, @factory … ============================================================================== 6. SAMPLE MATCH AUDIT ============================================================================== Strong matches (confidence >= 80): conf=100 @action_agent → enterprise-ai-platform entityType=commercial_agent_product conf=100 @advanced_ai_workflow_automatio → business-process-automation entityType=workflow_automation_tool conf=100 @agency_ai → ai-compliance-automation entityType=commercial_agent_product conf=100 @agency_cybersecurity → ai-compliance-automation entityType=commercial_agent_product conf=100 @agentos → banking-automation entityType=agent_platform Weak matches (50-79, needsTaxonomyReview=true): conf= 50 @3commas → algorithmic-trading-bot entityType=workflow_automation_tool conf= 50 @agentic_traders → algorithmic-trading-bot entityType=commercial_agent_product conf= 50 @agentictraders → algorithmic-trading-bot entityType=agent conf= 50 @agenticworkforce → shipment-tracking-agent entityType=commercial_agent_product conf= 50 @ai_agent_for_parcel_logistics_ → ai-supply-chain-agent entityType=commercial_agent_product (Per-Agent match reason is not persisted; signals computed are: slug-in-text +40, each suggestedQuery hit +25 cap 2, parent-sector keyword +8, Jaccard overlap up to +20.) ============================================================================== 7. DISCOVERED NICHE EXAMPLES ============================================================================== Top 15 clusters (emergent niches the seed taxonomy did NOT cover): agent--autonomous-research--computer-use-automation conf=60 status=merged Cluster of 16 unmatched agents sharing entityType=agent + homeClaw=c/meta. Top capabilities: autonomous research, computer use automation. Best existing-niche match was below 50. agent--autonomous-research--model-optimization conf=60 status=suggested Cluster of 16 unmatched agents sharing entityType=agent + homeClaw=c/meta. Top capabilities: autonomous research, model optimization. Best existing-niche match was below 50. agent--autonomous-research--self-evolution conf=60 status=suggested Cluster of 15 unmatched agents sharing entityType=agent + homeClaw=c/meta. Top capabilities: autonomous research, self-evolution. Best existing-niche match was below 50. agent--autonomous-research--task-automation conf=60 status=suggested Cluster of 16 unmatched agents sharing entityType=agent + niche=c/meta. Top capabilities: autonomous research, task automation. Best existing-niche match was below 50. agent--code-execution--workflow-automation conf=60 status=merged Cluster of 22 unmatched agents sharing entityType=agent + homeClaw=c/automation-operators. Top capabilities: code execution, workflow automation. Best existing-niche match was below 50. agent--deepseek-native--prefix-cache-optimization conf=60 status=suggested Cluster of 34 unmatched agents sharing entityType=agent. Top capabilities: deepseek native, prefix cache optimization. Best existing-niche match was below 30. agent--financial-automation--workflow-orchestration conf=60 status=merged Cluster of 16 unmatched agents sharing entityType=agent + homeClaw=c/markets-trading. Top capabilities: financial automation, workflow orchestration. Best existing-niche match was below 50. agent-framework--modular-agent-framework--cloud-deployment conf=60 status=suggested Cluster of 10 unmatched agents sharing entityType=agent_framework + niche=c/coding. Top capabilities: modular agent framework, cloud deployment. Best existing-niche match was below 30. agent-framework--observability--agent-framework conf=60 status=suggested Cluster of 32 unmatched agents sharing entityType=agent_framework. Top capabilities: observability, agent framework. Best existing-niche match was below 30. agent-framework--observability--memory-management conf=60 status=suggested Cluster of 21 unmatched agents sharing entityType=agent_framework + homeClaw=c/coding. Top capabilities: observability, memory management. Best existing-niche match was below 50. agent-framework--observability--multi-agent-orchestration conf=60 status=merged Cluster of 21 unmatched agents sharing entityType=agent_framework + homeClaw=c/coding. Top capabilities: observability, multi-agent orchestration. Best existing-niche match was below 50. agent-framework--observability--rag conf=60 status=suggested Cluster of 21 unmatched agents sharing entityType=agent_framework + niche=c/coding. Top capabilities: observability, rag. Best existing-niche match was below 50. agent-framework--observability--reinforcement-learning conf=60 status=suggested Cluster of 32 unmatched agents sharing entityType=agent_framework. Top capabilities: observability, reinforcement learning. Best existing-niche match was below 30. agent-framework--observability--workflow-automation conf=60 status=suggested Cluster of 32 unmatched agents sharing entityType=agent_framework. Top capabilities: observability, workflow automation. Best existing-niche match was below 30. agent-framework--reinforcement-learning--llm-agents conf=60 status=suggested Cluster of 27 unmatched agents sharing entityType=agent_framework. Top capabilities: reinforcement learning, llm agents. Best existing-niche match was below 30. ============================================================================== 8. SANITY CHECKS ============================================================================== No Agent row is force-matched if confidence < 50 → 573 unmatched agents (suggestedNiche=NULL). opportunityScore is no longer equal to expectedDensityScore for every niche → 266 of 348 niches have observed > 0, all of those now have opportunityScore < expectedDensityScore. High-coverage niches have lower opportunityScore (penalty kicks in) → see section 5: browser-automation-agent 69→9, agent-framework 64→4. Unmatched rows generate DiscoveredNiche suggestions → 186 DiscoveredNiche rows in DB. ============================================================================== 9. RECOMMENDED NEXT SLICE ============================================================================== Highest leverage: review the DiscoveredNiche set first. Several of the top-15 are obviously real, well-populated, agentic-economy niches that the seed missed: - commercial-agent-product--trading--investing - commercial-agent-product--desktop-automation - agent--medical-literature-search--evidence-synthesis - agent-platform--local-ai--conversational-ai Promote them (status='accepted') and rerun the scorer. The agents currently flagged unmatched will reattach, observed coverage on those promoted niches becomes real, and the unmatched count drops sharply. Other slice options: - build /opportunities UI viewer - extend seed taxonomy from 124 to 200 US niches - build the discovered-niche accept/merge/reject flow (closes the 'learning taxonomy' loop the brief described) END OF REPORT