Skip to content

Built for investigating, not just labeling

Every part of Triagic exists to answer one question faster: what actually happened, and why. Here is the whole product, thirteen surfaces under four verbs, and the guarantees underneath it. One seat plan, with optional add-ons for Checkups and Forms + email.

One path of four: a ticket, from arrival to reply

The most common path, in five steps, each governed by something an admin configures. The other three start from a question in the Console, a number on a dashboard, or a schedule, and run through the same agent.

  1. 1

    The ticket arrives

    By webhook, or by a poller that runs every two minutes. Emails, phone numbers, IDs, IP addresses and card numbers are redacted before any of it reaches a model, and then the identity fields are extracted: who this is about, and which account.

  2. 2

    Context is assembled

    Vector search pulls the five most similar past tickets with their confirmed root causes. If a PostHog funnel is configured, the step this user fell out of in the last 72 hours comes with it.

  3. 3

    A playbook is chosen

    A classifier matches the ticket against every enabled playbook's description and routing hints. Assigning one by hand pins it, and the classifier leaves that ticket alone from then on.

  4. 4

    The agent investigates

    Up to 25 tool iterations across the data sources that playbook allows. Every call is read-only, and every call is shown in the UI as it happens. The result is a root cause with evidence cited per system.

  5. 5

    A person answers

    The report drafts a reply to the customer. Someone reads it, edits it, and presses Send. The agent has no email tool, by construction.

  6. The pipeline in detail

    Every call in that sequence is logged with its model, tokens, latency and cost. An investigation is several calls and shows up as one folded total.

IntakeTickets and forms

Wherever your tickets already live

Connect the queue you have, or publish a form and start receiving your own. Ingest is webhook-first with a two-minute poller behind it, so a source works with only its credential filled in.

HubSpot, Zendesk, Jira, Slack
Each source carries its own filters, which gate the webhook and the poller identically. Jira also takes raw JQL when the filter fields aren't enough.
Auto-triage is off by default
Connecting a source starts ingest, not LLM spend. Tickets arrive, get embedded and classified, and wait for someone to hit Investigate now until you switch triage on. Pausing later stops the spend without losing the queue.
Your own hosted forms (add-on)
Build a public intake form in the portal: nine field types, up to 20 sections of 60 fields, and conditions that show a field only when another has a given value. Publishing versions the form, so an old submission still reads with the labels it was filled in against.
Hosted link or embedded
Share the link, or turn on embedding per form and drop it into your own site in an iframe. Embedding is off by default and a form with it off refuses to load inside a frame.
One email thread per request
A submission becomes a ticket with the customer's address on it. The acknowledgement, your replies and theirs all stay on that ticket in one thread. A reply can reopen a resolved ticket, and a resolve notice is available.
Attachments, bot check, theming
Up to five files per submission with a size limit you set between 1 and 10 MB, an optional Cloudflare Turnstile check, team notifications by email and Slack, and a logo, accent colour and font of your own.

IntakeLive chat

A chat bubble that rings the people on duty

Put a chat on your own site. A visitor writes, the desktop apps of the available people on the widget's team ring, and whoever accepts can investigate the chat before answering. Live chat is off until Triagic support turns it on for your organization.

One snippet, allowed sites
Paste the snippet before the closing body tag on every page that should show the chat bubble. Allowed sites go one per line, and chats from any other site are refused.
It rings who is available
Route a widget to a team, or leave the team empty and every available member of the organization is rung. Taking chats is the Available switch in the app's header.
End-to-end encrypted
Messages and files are encrypted between the visitor's browser and the agent's app. They pass through a relay run on Cloudflare, and neither Triagic nor Cloudflare can read them. Nothing is stored unless an agent saves the chat as a ticket.
Investigate this chat
Pick a playbook and the integrations to use. The same read-only reads as a ticket, every query shown, and a suggested reply that a person sends.
Save as ticket
The conversation becomes a ticket, or is added to the visitor's open one, so the evidence stays with the request.
When nobody is available
Show a message only, or one of your live forms with embedding turned on. Cloudflare Turnstile can check visitors are human before a chat starts.

InvestigateAuto-triage

Tickets that arrive already investigated

The desktop app is where the work happens. A triaged ticket opens with a conclusion, the evidence behind it, and the trail of everything the agent touched to get there.

The Tickets queue in the Triagic desktop app. Each ticket shows its source (form, Zendesk, HubSpot, Slack, Jira), the customer, the playbook it was routed to, its status and a one-line root cause.
The Tickets queue, in the desktop app. Demo workspace.
Root cause with cited evidence
The report names what broke and cites each system it came from. A root cause with three corroborating sources is worth more than a confident one with none, so the evidence is the part you read.
Every tool call, in order
Tool chips list what the agent called and when. Where it looked is as informative as what it found, and it's how you tell a good playbook from a wandering one.
Follow-up chat on the ticket
Ask a question under the investigation. It runs with the same playbook and the same allowlist, replays the last 20 turns, and is shared per ticket so a colleague can pick up where you stopped.
Re-investigate, or pin a different playbook
If the agent searched the wrong systems, assign a better playbook and run it again. Manual assignment pins the ticket so auto-classification will not overwrite your call.
Activity timeline
Notes, logged emails and attachments pulled from the source system, interleaved with what your team sent from Triagic. Opening a ticket re-syncs it and re-signs the attachment links.
Nothing is trapped in the app
Every prompt, every answer, every chat message and the whole investigation as markdown each have a copy button. Filter the inbox by playbook, including an explicit no-playbook view.

InvestigateConsole

Ask across every system at once

Not every question has a ticket behind it. A customer is on the phone, an alert fired, or you want to check something before anyone files anything. The Console is the same agent with no ticket attached.

A Console thread in the desktop app. The agent called propose_issues and drafted four issues for northwind/platform. Nothing is filed until someone reviews them.
A Console thread drafting issues, in the desktop app. Demo workspace.
Plain language, live tool calls
Ask what happened. The agent queries your databases, reads logs and checks metrics while you watch each call land. No pre-built dashboard to maintain.
Developer and support answers
One toggle sets who the answer is written for. Developer mode gives table names, error codes and log excerpts. Support mode rewrites the same finding in plain English with a suggested reply you can send as-is.
Pin a playbook to a thread
Applying a playbook's instructions and allowlist to a whole conversation makes it faster and stops it rummaging where the answer isn't. Leave it unpinned when you genuinely don't know where to look.
Threads that remember
Each investigation is its own thread, private to you, replaying the last 20 turns so a conversation builds. Tool traces stay in the UI and out of the model's context, so the audit trail costs no tokens.
Pick the model per thread
The picker offers your organization's configured deployments. Order of resolution is the thread's choice, then the install's runtime default, then the fallback.
Charts in the answer
Answers can render charts and diagrams inline, from the rows the agent read. Copy, Email and Create issue work on every answer.

InvestigatePlaybooks and knowledge base

Teach it your systems once

A generic agent gives generic answers. Playbooks, a knowledge base and scoped data sources are what turn it into somebody who knows your product.

Editing the Data import playbook: routing hints, the data sources it may use (postgres, opensearch, kubernetes) and its triage instructions.
The playbook editor, in the desktop app. Demo workspace.
Playbooks, per class of ticket
Four fields: a description and routing hints the classifier reads at ingest, triage instructions the investigating agent reads during the run, and the data sources the tool layer will allow. Different tickets need different procedures and different access. Admins can have one drafted from a prompt and revise it by asking.
Scope the tools, not just the prompt
A playbook's data-source allowlist is what the agent can see. Narrowing it makes runs faster and cheaper. Leave it empty and the agent gets everything, which is a fine place to start.
Knowledge base
Upload runbooks, product notes, escalation rules and exported sheets as Markdown, text, CSV, JSON, DOCX, PDF or XLSX, or connect Notion and Confluence to read live pages. The agent searches it before answering a product question and names the document it used. Admins can also describe a doc and have it written from your tickets and data, then revise it by prompt, keeping or discarding each change.
Document text is untrusted
Knowledge content is treated exactly like ticket text. Instructions written inside a document can't change how the agent behaves.
Teams and visibility
Playbooks can be organization-wide or restricted to selected teams. Team scoping governs who can use a playbook by hand; auto-classification still considers every enabled one.
The portal is the source of truth
Admins configure the organization in the web portal: members, teams, playbooks, shared credentials, knowledge, spend cap. Each desktop pulls that down on a schedule and runs against it.

WatchDashboards

Numbers you can open without spending AI

An admin describes what the team should watch. AI writes the queries once, and from then on the dashboard is those saved queries, run straight against your own data sources.

The Delivery operations dashboard: four KPIs with their change on the previous 30 days and a line chart of late deliveries, marked Free to view, 8 saved queries, 0 AI tokens per view, built for $0.25.
A dashboard, in the desktop app. Demo workspace.
Built from a prompt
Say what you want to see and pick the sources. Triagic reads their schemas and proposes KPIs and charts. Untick what you don't need, and each one you keep becomes one saved read-only query with its chart.
Priced before you pay
The proposal shows a build price per item, and every button that spends AI shows its price first. A per-run cap, $1.00 by default, stops a run that goes over and keeps what it already built.
Free to open and refresh
Opening a dashboard, switching between 7, 30 and 90 days and pressing Refresh replay the saved queries with no model. A broken query can be repaired by AI or edited by hand, and the hand edit is free too.
Your access, your machine
Queries run from each viewer's desktop over their own connections. A chart over a source someone can't open shows them a locked tile, and results are never sent to Triagic.

WatchAlerts

Told when a number goes bad

A dashboard syncs every 15 minutes, but nobody stares at it at 03:00. An alert rule watches one of its numbers and notifies people by how bad it is.

The Alerts page in the Triagic desktop app, on the Acknowledged tab. One critical alert, Late deliveries over 8% on the Delivery operations dashboard, fired at 9.4 against a threshold of 8, repeated twice and was acknowledged by a teammate 12 minutes later. Under it, the fixed severity ladder: which severities ring the bell, send a notification, email, post to Slack and repeat until acknowledged.
The Alerts page, in the desktop app. Demo workspace.
Rules from a prompt
Suggest alerts reads a dashboard's widgets and current numbers and proposes up to six rules, each with its reason. The Alert button on a chart turns one sentence into one rule for that chart. Both show their price first, nothing is saved until you press Save, and hand edits are free.
No model per check
Each check is the widget's saved read-only query and one comparison: above, below, or a percentage change on the previous period, for one to four checks in a row. Checking costs nothing.
One severity ladder, no settings
Low goes to the bell and a daily digest email at 09:00. Medium adds a desktop notification and a tone. High adds email to the rule's team. Critical adds the Slack alert channel and a notification that stays until it's dismissed.
Acknowledge, or it repeats
A critical alert repeats every 15 minutes, up to eight times, until it is acknowledged: by the owner in the app or, on a cloud-managed install, by a teammate from the Acknowledge link in the email. When the number recovers the alert resolves itself and everyone it reached is told.
The right desk, not everyone
The rule's owner always hears about it. Email also goes to one team: owners pick a team they belong to, admins can pick any team. Critical alerts post to the one Slack channel an admin sets.
Checked on the owner's desktop
Rules run on the owner's desktop app, over the owner's connections, while it is running. Closing the window on a Mac keeps it running. Quitting, sleeping, or closing the window on Windows stops the checks, so every rule shows when it was last checked.

WatchReports

A standing brief, every morning

A report is a playbook run on a schedule. Each run lands on the Reports page as a new edition, so the Console stays for the questions you ask yourself.

The Reports page in the Triagic desktop app. The rail lists two series by playbook, Payments & checkout every day at 07:30 and Platform reliability every Monday at 08:00, with their editions. The open edition, 7 of 7, is today's Payments & checkout brief: card declines at baseline, refunds up 12%, 14 orders stuck in payment_pending, with the 4 queries behind it folded under How this report was made.
The Reports page, in the desktop app. Demo workspace.
Editions, not threads
One series per playbook, with its cadence, such as every weekday at 09:00 in your time zone. Unread editions are marked and counted in the sidebar, and arrows step through earlier editions.
Watch it run, or don't
Open a running report to see the plan and each tool call as it happens. When it finishes, the trace folds into How this report was made, and a desktop notification tells you it landed.
Follow-up questions under the report
Ask below an edition and the answer runs under the same playbook and allowlist, with its own tool calls, shared with everyone who can see the playbook.
Run now, on the org's identity
Admins can start an edition straight away. Scheduled and manual runs use the organization's system identity and model credentials, never an individual's key, and show up in Usage.

WatchCheckupsAdd-on, priced per seat

The same agent, pointed at everything

A playbook answers why this broke for this customer. A checkup asks what is wrong across all of it: a standing read-only procedure you run on demand or on a schedule, against your systems and your own support history.

Fifteen curated procedures
Shipped with the app and there on first launch, across seven categories: cost and performance reviews, access and credential reviews, a PII exposure sweep, SLA and response quality, ticket trend analysis, incident readiness, GitHub and GitLab code review, and a SOC 2 readiness walkthrough.
Write your own, or generate one
Describe what you want reviewed and have the procedure drafted from the integrations you actually have connected, then edit it before it ever runs.
Watch it work, then keep asking
Follow a run live as it happens, get notified when the report lands, and keep questioning the report in its own thread. Anyone in the organization can ask follow-ups there.
A findings ledger, not a pile of reports
Findings keep their identity from one run to the next, so you can see what is new, what came back and what stayed fixed. Set a status, assign one, or promote it to a ticket that then gets triaged like any other.
Schedules, and scope per checkup
Run one now or on a cadence. Each checkup has its own data sources, and an empty setting means every server your organization has. App upgrades refresh the shipped content and never touch your scope, your schedule or your enabled flag.
Recommendations are proposals
A checkup that says drop this warehouse to size M has not dropped anything. Everything it produces is a suggestion for a person to apply, deliberately, in that system's own console.

ActIssues

From finding to the tracker

Integrations are how the agent reads your systems. Issue trackers are how a finished investigation leaves Triagic, as a draft a person checks first.

Create issue, drafted from the evidence
On any Console answer, report or ticket investigation. The draft carries the summary, root cause, evidence and a link back, and you pick the repository, labels and assignees before anything is posted.
Comment on the one that exists
Search the repository's own issues and post the same draft as a comment, or a note on GitLab, instead of filing a duplicate. Issues already filed from the same triage need an explicit confirmation.
A batch from one prompt
Paste a roadmap or a list of bugs into the Console and ask for issues. The agent drafts up to 15 at once, checks each against the repository's open and recent issues, and turns matches into updates. Nothing is filed until you review the batch.
Traceable both ways
Filed and commented issues show as linked issues on the ticket, and each filing and comment writes an audit entry with the provider, project and issue key.

ActSuggested replies

A person sends the answer

The investigation ends in a reply the customer can use: what broke, the workaround, what happens next. Someone reads it first, every time.

Drafted from the facts
The reply quotes the evidence the agent gathered. Support mode on a Console answer rewrites the same finding in plain English with a reply you can send as is.
What you see is what goes out
The draft opens in a dialog with the recipient prefilled from the ticket. There is no server-side rewriting, and the send is recorded on the ticket and in the audit log.
No email tool, by construction
The agent cannot send anything. Not disabled, not gated behind a permission: the tool does not exist.

ControlGuarantees

What it can't do is the feature

You are about to hand an AI agent credentials to production. The guarantees below are enforced in the tool layer and in the code path, not by asking a model to behave.

Read-only, filtered before the run
Write, mutate and delete tools are filtered out before any agent run sees them, when a server connects and again at every dispatch. Catalog integrations expose only the tool names verified as reads; any other server has to annotate a tool read-only or it isn't exposed at all.
Your credentials, least privilege
A handful of upstream servers have no read-only mode of their own, and those are named in the docs. Point every integration at a read-only user or a read-scoped token and the guarantee stops depending on any single layer being bug-free.
PII redaction on every path
Emails, phone numbers, national ID numbers, IPv4 addresses and Luhn-valid card numbers are stripped from the subject, body and metadata before a prompt is assembled. Background triage, the Console, ticket chat, classification and similar-ticket search all run it. None of them skip it.
Encrypted at rest, twice
Credentials are AES-256-GCM encrypted under the platform key, and re-encrypted on arrival under a key that never leaves that machine. No endpoint and no admin screen returns a plaintext secret; API responses carry masked values only.
Shared credentials without sharing them
A member can use a shared integration and cannot recover its secret or repoint it. The member-facing view has no credential fields at all, not even masked ones, and editing shared configuration takes an admin.
Append-only audit log
Every mutation to authentication, organizations, teams, playbooks, integrations, issue trackers, filed issues, emails sent and playbook assignment writes a row with actor, action, target, before and after, and a timestamp. Admins only, enforced by the service rather than hidden in the nav.
A spend cap that actually stops runs
One monthly USD number for the organization. Every LLM call is logged individually with its model, token counts, latency and cost, snapshotted at write time so correcting a price later never rewrites history.
Cost and latency you can read
The Usage page carries totals, per-model latency percentiles, a per-task split and a daily cost chart, with links back to what caused each call. An investigation folds its several calls into one number.

57 integrations, plus anything you already run

Each one asks for its own credential and nothing else. The package, arguments and transport behind it are derived for you, so upgrades reach existing configurations on their next restart. Add a catalog entry twice for production and replica, tag each with its environment, and scope a playbook to exactly one of them.

Anything else
Point Triagic at your own MCP server, as a command or a remote HTTP endpoint. It goes through the same read-only tool gate as everything in the catalog.
Bring your own model
Connect your own provider credentials and every call runs against your own contract and rate limits. Ollama is on that list, so the model can stay on your hardware too.Azure OpenAI, OpenAI, Anthropic, Google (Gemini), OpenRouter, Ollama
Nothing to install first
Most integrations spawn a local process, so the installer ships a portable Node LTS and a portable uv ahead of the app's own PATH. Every integration runs on the same runtime whatever the machine has on it. Five talk to hosted endpoints over HTTPS and need no runtime at all; three run in Docker, which is the one thing you install yourself.Per-integration setup steps

What Triagic deliberately doesn't do

These are design decisions, not gaps in the roadmap. Each one is the reason someone is willing to connect production in the first place.

It doesn't write to your systems
There is no write path to enable. The tool filter is global and applies to ticket investigations, Console questions and checkups alike.
It doesn't email anyone
The agent has no email tool. Not disabled, not gated behind a permission. A person opens the draft, edits it, and presses Send.
It doesn't copy your data anywhere
No pipeline, no warehouse sync, no third-party copy of your database. The app runs on your machine, against your systems, over your network. If you need a VPN to reach production, so does Triagic.
It doesn't resell you model capacity
Your provider key, your contract, your rate limits. Triagic never proxies model spend through a shared account.
It doesn't reclassify old tickets quietly
Classification runs at ingest or on an explicit re-investigation. A ticket already in the inbox will not silently pick up a playbook written afterwards.
It doesn't certify anything
The SOC 2 readiness review is an evidence-collection exercise, not an audit and not a certification. Only a licensed CPA firm can perform a SOC 2 examination.

See it work on a real ticket

Every feature on this page is unlocked from day one. Start a 14-day free trial, no credit card required.