The Corporate AI OS. One app instead of nine.
Chat, board, drive, wiki, email, notes, calendar, CRM and meetings in a single private system, with an evidence-grounded AI layer over all of it. Because it all runs in one place, an answer can cite a message, a file, and something a person said out loud last quarter.
Ask, the front door
One box, pointed at everything your organization knows. Ask returns an answer with the underlying evidence attached, clickable citations that open the exact source chunk, so nobody has to take the summary on faith.
Three independent modes stack on the same question. Conversation is the fast path. Evidence forces every claim back to a retrieved source. Agentic lets it take steps, search, read, cross-reference, and shows its work. With all three off, you get the fast model and a straight answer.
Upload a file mid-question and it is chunked into the corpus immediately, then available to every later question. Voice input has real silence detection, so it stops when you stop talking.
- Numbered citation chips that jump to the source
- Mode, model and latency stated on every answer
- Agentic step trace when the agent took actions
- Sources · claims · contradictions indexed, live
- Regenerate and copy on every response
Search, retrieval with nothing in the way
Sometimes you don't want an answer, you want the raw material. Search runs direct vector retrieval across the whole corpus and returns the top-ranked chunks with their scores, no synthesis layer in between. It is the debugging view for your own knowledge base: if Ask said something surprising, Search shows you exactly what it was reading.
The workspace, what it replaces
These are not integrations pointing at other products. They are the products, running inside Felarity, writing into the same corpus that Ask reads. That is the whole point: context stops being scattered across nine tools with nine permission models.
Chat replaces Slack
Channels, threads and direct messages. Anything said here is evidence like anything else, a decision made in a thread is retrievable six months later without anyone remembering to write it down.
Board replaces Jira
Tickets, columns and sprints that stay tied to the conversation where the work was actually agreed, so "why are we doing this?" has an answer with a timestamp.
Drive replaces Google Drive
Files indexed the moment they land rather than the week someone remembers to share them. Every upload is chunked, embedded and immediately answerable.
Wiki replaces Confluence
Documentation the Ask layer reads directly, so the page and the answer can't quietly drift apart the way a stale wiki always does.
Inbox and triage in the same system as everything the mail needs to be read against, the contract, the thread, the meeting where the terms changed.
Calendar
What's coming, with a pre-meeting brief assembled from everything the attendees have said before, including the places their prior statements disagree.
CRM
Accounts and pipeline that update from the call itself rather than from a rep's end-of-week recollection of the call.
Commitments
Who promised what, to whom, by when, extracted automatically from meetings and messages, then tracked until it's closed out.
Notes & Whiteboard
Scratch thinking that gets indexed with everything else instead of dying in a personal doc nobody else can see.
Governance
Evaluation, usage metering, audit trail, SSO, two-factor and API keys. The boring parts, included rather than sold as a tier-four add-on.
Bots and automation
Standing jobs that run against the corpus on a schedule and tell you when something changed, a claim contradicted, a commitment slipping, a document that no longer matches the filing it references. Automation that watches your own record rather than shuttling data between two SaaS products.
App Builder
Build an internal tool against your own data without opening an engineering ticket. Describe what you need, get a working surface backed by the same corpus, the same permissions and the same audit trail as everything else in the system.
Connectors, or keep the tools you have
Replacing everything at once is not how real organizations move. Eighteen connectors across seven categories let Felarity index what you already use while you decide what to migrate, meetings, chat, docs, code and tickets, storage, email, and AI advisors.
Built in
Live Recorder · Upload & URL
Meetings & chat
Google Meet · Microsoft Teams · Zoom · Slack
Docs, code & mail
Confluence · Notion · Google Drive · OneDrive & SharePoint · Jira · Linear · GitHub · Gmail · Outlook
AI advisors
Claude · ChatGPT · Gemini
Live meeting intelligence
The moment a session starts, the browser captures audio in five-second chunks and streams them to our gateway. our speech-to-text model transcribes on dedicated GPUs and returns aligned text within roughly a second of the spoken word. As each utterance lands, the deep council compares it to everything said earlier in the session, scoring whether the new statement contradicts, qualifies, or commits the speaker to something they previously denied.
Credibility arcs update per speaker as the meeting unfolds. Hedge density rises, certainty shifts, a promise is made and then quietly walked back two minutes later, these are surfaced to the side panel in real time, not buried in a transcript you have to re-read at midnight.
- Contradiction alerts with cited prior utterance
- Per-speaker credibility arc (rising / falling / stable)
- Hedge and certainty drift
- Unkept commitments and forgotten promises
- Council-flagged escalations from the industry panel
- Side-panel intel cards as evidence accumulates
The post-session forensic pipeline
When the meeting ends, the eleven-stage pipeline runs against the full session, not the chunked live stream, but the reconstructed whole. Each stage emits a progress event over SSE so the workspace UI can show what is happening in the moment, and each stage's output becomes input to the next.
post_concat, Concatenate the chunked audio back into a continuous, gap-aware recording for whole-session analysis.Required because chunk boundaries break diarization and acoustic features.post_diarize, Run our speaker-diarization model speaker diarization against the full session to bind utterances to speaker identities with higher confidence than the live pass.post_acoustic, Extract speech rate, pause distribution, and stress markers per speaker.Inputs into the credibility model and the confrontation classifier.post_confrontation, Classify confrontation and response pairs: was a hard question asked, what was the answer's structure, did the speaker deflect, pivot, or commit.post_samples, Extract a four-second voice sample per speaker for the report, so reviewers can verify who said what against the transcript.post_attribute, Bind the contradictions detected during the live phase to the speakers identified by the full-session diarization, correcting any drift from the live attribution.post_nli, Re-score contradiction pairs with an independent verification model natural language inference on CPU, producing entailment, neutral, and contradiction probabilities that survive scrutiny outside the room.post_topology, Build a NetworkX graph of statements, contradictions, and confrontations, then classify the meeting's pattern: hostile cross-examination, evasive consensus, productive disagreement, or rehearsed alignment.post_council, Deep council re-analysis with full speaker context. The industry panel reviews the now-attributed evidence and produces the final analyst commentary.post_attest, Build a sealed attestation chain over the audio, transcript, diarization, contradictions, NLI scores, topology, council output, and metadata, then sign the root with digital signature.post_complete, Render the final report: contradictions with citations, credibility arcs, confrontation map, council commentary, and the attestation block.
Cryptographic attestation
Every completed session ships with a hash tree whose leaves are the cryptographic hashes of the audio, transcript, diarization, detected contradictions, NLI re-scoring, topology graph, council output, and session metadata. The root is cryptographically signed using our published signing key. The signature, the public key fingerprint, and the leaf hashes travel inside the report itself.
Any third party, opposing counsel, a regulator, an auditor, an arbitrator, can take the report, recompute the leaves against the artifacts, rebuild the root, and verify the signature against our published public key without ever talking to Felarity. The verifier endpoint at /api/verify performs the same check in-browser for convenience, but the math does not require it. If a single transcript line, audio segment, or council finding has been altered after sealing, verification fails.
30 industry councils
Every workspace selects an industry on creation. The council for that industry is a named panel of analyst personas, each one a specialist role that critiques the same content from a different angle. The same paragraph of meeting transcript that looks unremarkable to a generalist looks load-bearing to a regulatory affairs lead, and dangerous to an ethics officer. The council surfaces all of those readings at once and the synthesis layer reconciles them with attribution.
Exports and shareable reports
Reports export to PDF with the full attestation appendix bound in, to Markdown for ingestion into matter-management or knowledge-base systems, and to JSON for programmatic downstream use. Each export carries the same signature as the source record, exporting does not break verifiability. For sharing outside the workspace, generate a password-protected read-only link with a hard expiry; revoke at any time from the workspace admin panel. Share-link access is logged per view with IP and user-agent in the workspace audit trail.
API and integrations
The REST API uses key-scoped Bearer tokens prefixed flrt_, each one issued against a specific workspace with its own rate limit and its own audit trail. Every authenticated call writes a row to the per-key event log, which is queryable from the admin surface and exportable to your SIEM. The full OpenAPI specification is at /api/openapi.json, and webhooks fire on report.ready, contradiction.flagged, and verification.failed so your downstream systems can pull the attested report as soon as the pipeline completes.
SAML SSO covers Okta, Azure AD, and Google Workspace on Professional and above. SCIM 2.0 user provisioning is available on the Enterprise tier. Slack notifications post contradiction alerts and report-ready events into the channel of your choice, with the share link and the attestation fingerprint inline.
Self-hosted and dedicated tenancy
Enterprise customers can run Felarity on dedicated infrastructure, a single-tenant VPC managed by our team, or fully on-premise inside your own environment. Both options support bring-your-own-key LLM, so the council, the synthesis layer, and the NLI scoring can route through the model your security team has already approved rather than the one we ship by default. No meeting content transits a shared model. Dedicated and on-prem deployments are bookable through sales.
Walk through the product.
Bring a sample meeting or use ours. We will run the live phase and the full forensic pipeline against it on a call, and you keep the attested report.