| name | sales-notably |
| description | Notably (notably.ai) platform help — an AI-forward qualitative research repository and synthesis tool: import interview transcripts, notes, survey open-ends, and audio/video, then auto-transcribe, AI-tag, cluster by theme and sentiment, and generate insight summaries on a split-screen data-driven canvas, stored in a searchable cross-project repository with template-driven analysis and shareable highlight clips. Use when synthesizing user interviews into themes, analyzing open-ended survey responses, building a searchable research repository, tags disappearing when switching sections, choosing between Notably and Dovetail/Condens/Marvin, or exporting insights when there is no API. Do NOT use for choosing a qualitative-analysis tool across the market (use /sales-customer-feedback) or recruiting and running studies end-to-end (use /sales-great-question). |
| argument-hint | [describe what you need help with in Notably] |
| license | MIT |
| version | 1.0.0 |
| tags | ["sales","customer-cx","platform"] |
Notably Platform Help
Notably (notably.ai) is an AI-forward qualitative research repository + synthesis tool — the analysis end of the research stack, a peer of Dovetail, Condens, Marvin (HeyMarvin), and Aurelius. You already have the data (interview transcripts, session notes, open-ended survey responses, audio/video, whitepapers); Notably ingests it, auto-transcribes, AI-tags and clusters by theme/sentiment, and generates insight summaries on a split-screen data-driven canvas that keeps the raw data next to the insight, then stores everything in a searchable cross-project repository. A template library (debrief → analysis → insights) guides each stage, and findings ship as insights (with AI imagery) and highlight clips you can share with free viewer seats.
Two things to say almost every time:
- Notably ANALYZES data — it does not recruit, schedule, or generate it. It has no participant panel and runs no studies. If the user needs to find and talk to users end-to-end (recruit → run → repository), that's the all-in-one research-ops job — route to
/sales-great-question. Notably starts after you have transcripts/notes.
- Notably has NO public API, webhooks, MCP server, or documented Zapier. The only integrations are Miro and FigJam (import/sync from a whiteboard), plus imports from surveys/notes/audio/video; data-out is manual export. A "pipe insights into my CRM/warehouse" ask is a manual/scheduled export job, not an endpoint call — a documented REST/webhook pipeline belongs to
/sales-userintuition.
Step 1 — Gather context
If references/learnings.md exists, read it first for accumulated platform knowledge.
Ask only what you can't infer:
- What do you want from Notably?
- A) Import & transcribe — bring in transcripts/notes/audio/video/survey open-ends
- B) Analyze — AI tagging, theme/sentiment clustering, the data-driven canvas, templates
- C) Synthesize & share — insight summaries, highlight clips, viewer sharing
- D) Repository — cross-project search, organizing data across studies
- E) Get data out — manual export (no API); Miro/FigJam sync
- F) Choose a plan — Free (limited) vs Pro vs Team vs Enterprise
- Do you already have the raw research data, or do you still need to recruit/run the study? The second is a research-ops question — flag it in Step 2 and route to
/sales-great-question.
Skip-ahead: if the prompt already names the task or the question is specific, go to Step 3.
Step 2 — Route or answer directly
| If the user's question is about… | Route to |
|---|
| Choosing a qualitative-analysis / research-repository tool across the market, or VoC/feedback strategy | /sales-customer-feedback {question} |
| Recruiting + running studies end-to-end (panel, scheduling, all methods) then storing them | /sales-great-question {question} |
| Validating whether to build an idea (the evidence ladder, AI scores, smoke tests) | /sales-idea-validation {question} |
| A documented API / webhook-native research pipeline (Notably has none) | /sales-userintuition {question} |
| Running AI-moderated interviews to generate the data first | /sales-great-question or /sales-idea-validation {question} |
When routing, give the exact command: "This is a {domain} question — run: /sales-great-question {original question}"
Otherwise, answer Notably-specific questions using Step 3.
Step 3 — Notably platform reference
Read references/platform-guide.md for the full reference — the module/automation-surface table (what's UI-only vs export-accessible), best-effort pricing and plan gates (Free vs Pro vs Team vs Enterprise, viewer seats), the Project → data → tag → theme → insight data model, the import sources and Miro/FigJam sync, and the no-API data-out playbook. Notably has no REST API, so there is no API-reference file.
Answer using only the relevant section — don't dump the full reference.
Step 4 — Actionable guidance
- In every response, verify AI output against the source verbatim. Notably's AI tagging, theme clustering, and insight summaries are a starting draft, not a finding — tell the user to click into the verbatims/quotes underneath each theme and confirm the AI read the data correctly before presenting an insight. Say this even when the user only asked how to speed up synthesis: AI acceleration is the value, but an unverified AI theme can misrepresent what a participant actually said.
- Draw the analysis-only boundary head-on whenever recruiting/data-collection comes up. Notably does not recruit participants, schedule sessions, or run interviews — it only analyzes data you already have. If the user has no transcripts/notes yet, say so plainly and route the recruit-and-run job to
/sales-great-question (all-in-one research-ops) or the interview-generation job to /sales-idea-validation. Notably is the wrong first pick when there's no data yet.
- Flag it as export-only when any automation/API/pipeline comes up. Notably has no public REST API, webhooks, MCP server, or documented Zapier (verify — it may change). The only data-out is manual export, and the only live integrations are Miro and FigJam (import/sync, not a data-out pipeline). "Sync insights to HubSpot/Snowflake on a schedule" is a manual/scripted export job, not REST — if a documented pipeline is required, route to
/sales-userintuition.
- Warn about the tags-disappearing bug and save often. A recurring, reproducible complaint is that tags/highlights can vanish when moving between sections of the canvas. Tell the user to refresh to confirm whether a tag was truly lost vs a render glitch, apply tags in small batches, and re-check the tag/theme view after navigating — don't assume a single un-verified pass captured everything.
- Present pricing as best-effort and match the plan to the job. Best-effort tiers: Free (limited) → Pro ~$21/user/mo → Team ~$200/user/mo → Enterprise (custom); viewer/observer seats are free for sharing insights externally. Frame the choice around how many researchers need to tag/analyze (paid seats) vs how many stakeholders just need to read insights (free viewers) — point to notably.ai/pricing to confirm.
- Match Notably to the moment in the workflow, and walk the synthesis steps. Recommend it for the synthesis step — turning a pile of transcripts/notes/open-ends into themes, insights, and a searchable repository. When the user asks how to run that synthesis, spell out the workflow: the data into a → apply a (debrief → analysis → insights) → let AI on the → generate and to share via free viewer seats. Name its AI-forward edge over Dovetail/Condens (auto theme extraction + insight summaries) its limit (analysis-only, thin automation); for a lighter/cheaper repository, note ; for the enterprise repository incumbent, .
If you discover a gotcha or tip not in references/learnings.md, append it there with today's date.
Gotchas
Best-effort from research (2026-07) — pricing, plan gates, the tags-disappearing bug, and the export-only surface; the live site was unreachable at research (SSL/bot-block) so specifics lean on third-party sources — verify at notably.ai.
- Analysis-only — no recruiting, scheduling, or data generation. Notably starts after you have data. No participant panel, no studies. For recruit → run → repository, use
/sales-great-question.
- No REST API, no webhooks, no MCP, no Zapier. The only integrations are Miro and FigJam; the only data-out is manual export. Don't design a live pipeline around it — route pipeline needs to
/sales-userintuition.
- AI insights are a draft, not a finding. Auto-tags, theme clusters, and summaries can misread nuance — always confirm against the underlying verbatims before presenting an insight.
- Tags/highlights can disappear when switching sections. A reproducible bug — tag in small batches, refresh to confirm, and re-check the tag view after navigating.
- Free tier is a real cap; Team is a steep jump. Best-effort Free (limited) → Pro ~$21/user/mo → Team ~$200/user/mo → Enterprise (custom). Use free viewer seats for read-only stakeholders instead of paying for a full seat.
Related skills
/sales-customer-feedback — The tool-agnostic qualitative-analysis / VoC strategy and the full research-repository landscape (use this to choose an analysis tool, or for NPS/CSAT/survey strategy). Install: npx skills add sales-skills/sales --skill sales-customer-feedback -a claude-code/sales-great-question — The all-in-one research-ops peer that recruits and runs studies (panel + scheduling + every method) then stores them in a repository — the pick when you have no data yet. Install: npx skills add sales-skills/sales --skill sales-great-question -a claude-code/sales-idea-validation — The validate-before-building method + the full research/validator landscape; where a research-repository tool fits among validators, synthetic research, and interview tools. Install: npx skills add sales-skills/sales --skill sales-idea-validation -a claude-code/sales-userintuition — The API/webhook/MCP-native research peer — the pick when you need a documented programmatic pipeline Notably can't offer. Install: npx skills add sales-skills/sales --skill sales-userintuition -a claude-code/sales-trill — The free, public-beta synthesis peer — same analysis job (interview transcripts → AI insights + theme categorization → Notion-like report) but lightweight and free (no paid tiers); also no API. The budget alternative when Notably's price or feature depth isn't needed. Install: npx skills add sales-skills/sales --skill sales-trill -a claude-code/sales-do — Not sure which skill to use? The router matches any sales objective to the right skill. Install: npx skills add sales-skills/sales --skill sales-do -a claude-code
Examples
Example 1: "I ran 12 user interviews — how do I turn the transcripts into themes fast?"
User says: "I have a dozen interview recordings and messy notes. I want themes and a summary I can share, not to code every line by hand."
Skill does: Recommends importing the recordings (auto-transcription) and notes into a Project, running a template (debrief → analysis → insights), letting the AI tag and cluster by theme/sentiment on the data-driven canvas, then generating an insight summary + highlight clips to share via free viewer seats. Insists the user click into the verbatims under each theme to confirm the AI read them correctly before presenting, and warns to tag in small batches / refresh because tags can drop when switching sections.
Result: The user gets a verified, shareable set of themes and insights in a fraction of manual-coding time.
Example 2: "Can I pull Notably insights into our warehouse / automate the export?" (developer/automation)
User says: "I want our research insights flowing into Snowflake automatically instead of clicking export every week."
Skill does: States plainly that Notably has no public REST API, webhooks, or MCP server — the only integrations are Miro and FigJam (import/sync, not a data-out pipeline), and the only data-out is manual export. Suggests a scheduled manual/scripted export → ETL as the workaround, notes there's no programmatic pull so it's batch, not a live sync, and — if a documented REST + webhooks pipeline is a hard requirement — routes to /sales-userintuition.
Result: The user builds a manual-export → ETL job instead of hunting for an API that doesn't exist.
Example 3: "Should I use Notably or Great Question — and is Notably like Dovetail?"
User says: "I'm picking a research tool. We haven't recruited anyone yet. Is Notably basically Dovetail?"
Skill does: Clarifies that Notably is analysis-only (a Dovetail-style repository + AI synthesis tool that starts after you have data), and its edge over Dovetail/Condens is being the most AI-forward (auto theme extraction + insight summaries). Because the user hasn't recruited yet, flags that Notably is the wrong first pick and routes the recruit → run → repository job to /sales-great-question; for choosing among analysis tools across the market, routes to /sales-customer-feedback.
Result: The user picks the right tool for their stage — Great Question now, Notably (or Dovetail) once they have data.
Troubleshooting
"My tags/highlights disappeared when I switched sections."
Symptom: Tags or highlights applied on the canvas seem to vanish after navigating between views.
Solution: This is a reproducible Notably complaint. Refresh the view to confirm whether the tag was truly lost or just not re-rendered; apply tags in small batches rather than one long pass; and re-check the tag/theme view after navigating before assuming a study is fully coded. If tags are genuinely lost, re-apply and report it to Notably support — and keep your source transcripts as the ground truth.
"The AI theme doesn't match what the participant actually said."
Symptom: An auto-generated theme or insight summary reads as off, generic, or overstated.
Solution: Treat AI output as a draft, not a finding. Open the verbatims/quotes underneath the theme on the split-screen canvas and confirm the AI clustered them correctly — re-tag or split the theme where it conflated distinct points. The value is acceleration; the accuracy check is yours. Feed cleaner, well-scoped source data (good transcripts, clear notes) for better clustering.
"How do I get data in and out — and can I automate it?"
Symptom: The user wants imports set up and results flowing into other tools.
Solution: In: import transcripts/notes/audio/video/survey open-ends/whitepapers, and sync from Miro or FigJam. Out: manual export only — Notably has no public REST API, webhooks, or MCP, so there's no programmatic pull and no live sync. Script/schedule the manual export into your own ETL if you must, and route any documented-pipeline requirement to /sales-userintuition.
