Failed deploy
Tom Reilly, platform engineer at BigCo, asked why the last deploy_api run failed. Memtro read the execution, named the failed stage and its error, and said who had triggered the run.
Harness + Memtro
Why did the last deploy_api run in Harness fail?
Harness connects Memtro to your CI/CD. It reads organizations, projects and pipelines with their last run, and executions by status with stage counts, failures and durations. For one run it reads each stage's status and the error, and it lists pending approvals, services and environments. When asked and granted, it can run a pipeline, retry a failed run from given stages, abort a run or mark it failed, approve or reject an approval step, and tag or annotate a run. A CD pipeline deploys when it runs, and an abort does not undo what has already deployed.
In Memtro
What you can do with Harness in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Harness tool, reads what it needs, and answers with the source cited.
What it does
- 01Lists organizations, projects and pipelines with stage count, last run status and recent error count.
- 02Lists executions by pipeline and status with run number, trigger, who ran it, duration and the error.
- 03Reads one execution's stages, its approval steps with deadlines, and the services and environments Harness deploys to.
- 04When asked and granted, runs a pipeline or retries a failed run. A CD pipeline deploys and the pipeline's own notifications go out.
- 05When asked and granted, aborts a run or marks it failed, which runs its failure strategy, and approves or rejects an approval step, which can release a deployment.
- 06When asked and granted, tags a completed run or sets its notes. Nothing runs and nobody is notified.
Acts when asked
When you ask it to
These tools change something in Harness. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
- 01Run a pipeline (a CD pipeline deploys)
- 02Retry a failed pipeline run from given stages
- 03Abort a running pipeline execution
- 04Mark a pipeline execution as failed
- 05Approve or reject a Harness approval step
- 06Add tags to a completed pipeline execution
- 07Set the notes on a pipeline execution
In practice
Ask it like you would a colleague
Once Harness is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Harness + Memtro
Why did the last deploy_api run in the payments project fail?
Which pipeline runs are waiting on approval?
Which runs failed this week in the checkout project?
Which environments does the payments project deploy to?
Retry yesterday's failed deploy_api run from the deploy stage.
Release approval
Sarah Chen, engineering manager at Northwind, asked Memtro to approve the waiting approval step on the release pipeline. As granted, Memtro approved it as the key's user with her comment, and the gated deployment went ahead.
Teams
Where it fits
The teams that lean on Harness most, a question each of them asks, and what they connect beside it.
- EngineeringKeep decisions from evaporatingEngineer, Tech lead, On call, New joiner“Who owns the billing migration, and what did we decide about retries?”Used alongside GitHub, Linear, Jira, Confluence, Slack and 5 more.
- ProductHear what customers actually ask forProduct manager, Researcher, Designer, Head of product“Which customers asked for SSO this quarter, and what is their combined ARR?”Used alongside Help Scout, HubSpot, Linear, Jira, Slack and 6 more.
- Agent buildersMemory and tools for the agents you buildSolo builder, Platform team, Automation engineer, Whoever signs it off“Search memtro for what we know about Acme before drafting the proposal”Used alongside GitHub, Linear and Slack.
Better together
Works with
A record in Harness is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
- Work managementHarness with JiraJQL search, issue details and projects from Jira Cloud.
- Work managementHarness with Clio ManageAsk the matter: its client, its fee earner, the time on it and what is still unbilled.
- Work managementHarness with LinearIssues, projects and teams, synced hourly into memory.
- SupportHarness with Help ScoutAI that reads your support conversations and cross-references the customer everywhere else.
- SupportHarness with ZendeskEvery ticket, reply and internal note, ready to be asked about.
- SupportHarness with IntercomCustomer conversations and the people behind them, in your company memory.
- Documents and wikisHarness with NotionSearch pages and query databases, and write to them when you ask.
- Documents and wikisHarness with Google DriveSearch Drive and read Docs, Sheets and Slides as text, and write a Doc when you ask.
- Documents and wikisHarness with ConfluenceSearch and read wiki pages, and write them when you ask.
Also in Engineering and operations
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
- GitHub
- AWS CloudWatch
- Sentry
- ServiceNow
- Okta
- Twilio
- AWS CloudTrail
- GitLab
- Bitbucket
- Vercel
- PagerDuty
- Datadog
- Grafana
- incident.io
- Azure DevOps
- CircleCI
- Cloudflare
- LaunchDarkly
- New Relic
- Rollbar
- Snyk
- Better Stack
- Buildkite
- DigitalOcean
- Heroku
- Netlify
- SonarQube Cloud
- Statuspage
UptimeRobot- Axiom
- BugSnag
- Checkly
- Hetzner Cloud
Honeycomb- Pingdom
- Render
- Statsig
- Sumo Logic
- Supabase
- HCP Terraform
- Vultr
- Airbrake
- Codecov
Cronitor- Dynatrace
FireHydrant- Fly.io
- Honeybadger
- Akamai Linode
- Octopus Deploy
- Pulumi
- Rootly
- Semgrep
- Splunk
StatusCake- Tailscale
- Argo CD
- authentik
- Coolify
- Gitea
GlitchTip
GLPI- Jenkins
Langfuse
LibreNMS- n8n
NetBox- Portainer
- Prefect
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone- OpenAI (usage and cost)
- Anthropic (usage and cost)
- Algolia
- Flagsmith
- Unleash
GrowthBook
Drata
Intruder
GitGuardian
Secureframe
ilert- KnowBe4
JumpCloud
ConfigCat- Railway
- Fastly
- Postman
- Make
- Braintrust
- OpenRouter
- ElevenLabs
Split- Scaleway
Aikido Security- AssemblyAI
Astronomer- Bamboo
- Baseten
- Bitrise
- Bitwarden
- BrowserStack
- bunny.net
- Cachet
- Checkmk
- Civo
- Cloudsmith
- Codacy
- Codemagic
Comet Opik- Coralogix
CrowdStrike Falcon- Dagster+
- DeepSource
Detectify- Docker Hub
Domotz- Grafana OnCall
- Hugging Face
- Instatus
- Koyeb
- Lambda Cloud
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary- Mezmo
NinjaOne- Nomad
Northflank- Oh Dear
- OVHcloud
Portkey- Probely (Snyk API & Web)
PromptLayer- Proxmox VE
PRTG Network Monitor- Qase
Raygun
Retell AI- Retool
Runpod- SecurityScorecard
- Semaphore CI
Shodan- SigNoz
- Socket
Spike.sh
Squadcast- SwaggerHub
- TeamCity
Tenable- Together AI
- Travis CI
UpGuard
Uptime.com
Vanta- Vapi
- Windmill
Zenduty- OpsLevel
Cortex- Auth0
- Clerk
WorkOS
Kandji
Automox
Huntress- HackerOne
SimpleMDM- AppSignal
Healthchecks.io
Rapid7 InsightVM- 1Password Events
- JFrog Artifactory
- Sauce Labs
Zenhub- Deepgram
- Replicate
Setup
How to connect
Connect withAPI key token and account ID
- 1
In Harness, open My Profile, My API Keys, add an API key and a token with an expiry, and copy it. A service account token limited to viewing and executing chosen pipelines is safer.
- 2
In Memtro, open Connections → Harness and paste the API key token and your Account ID, from any Harness URL.
- 3
An administrator grants the actions by name, such as running pipelines, to the teams that may use them. Set the Host only for a vanity or self-managed Harness.
- 4
Ask why the last deploy_api run in payments failed.
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Harness tools are the same everywhere.
FAQ
Questions
Can Memtro change anything in Harness?+
Only when you ask, and only what it has been granted: run a pipeline (a CD pipeline deploys); retry a failed pipeline run from given stages; abort a running pipeline execution; mark a pipeline execution as failed; approve or reject a Harness approval step; add tags to a completed pipeline execution; set the notes on a pipeline execution. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
Who can use a Harness connection?+
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Does Memtro store my Harness data?+
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
How do I connect Harness?+
API key token and account ID. In Harness, open My Profile, My API Keys, add an API key and a token with an expiry, and copy it. A service account token limited to viewing and executing chosen pipelines is safer.
Connect Harness in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.