
Agent Obsessed , caffeine fuelled, productivity machine @datadoghq. ❤️ all things 🍎, Microservices, AI, Agents. Ex VMware, MVP, CTP, etc.
Dublin, Ireland
Joined February 2011
- Tweets19.6K
- Following2.2K
- Followers5.1K
- Likes9.2K
Andrew Morgan retweeted
Last week, we announced our own LLM Model for root cause investigations Scout
See it in action below
A database is struggling. The root cause? A node rotation two hours earlier.
See how Scout 1.0 powers Datadog Bits Investigation to follow the evidence from symptoms to root cause.
Comparable performance at 3–8x lower inference cost on our benchmark - @datadoghq 👇
Andrew Morgan retweeted
LAUNCHED: Skills Library for Datadog Bits AI agents
Turn investigations, notebooks, and team knowledge into reusable skills your agents can use across workflows.
Teach your agents once. Reuse that expertise everywhere.
See it in action 👇
@datadoghq
Amazing work by the Datadog team! A frontier SRE model at a fraction of the cost!
Meet Scout 1.0, our first AI model built for investigating production incidents.
Scout matches frontier-model investigation quality at a fraction of the cost, which makes it practical to investigate more issues, earlier.
We trained Scout on realistic simulations built from real-world incidents and production telemetry, using reinforcement learning to reward accurate root causes backed by evidence.
Learn more and sign up for the preview: bit.ly/3TJknGO
Andrew Morgan retweeted
Meet Scout 1.0, our first AI model built for investigating production incidents.
Scout matches frontier-model investigation quality at a fraction of the cost, which makes it practical to investigate more issues, earlier.
We trained Scout on realistic simulations built from real-world incidents and production telemetry, using reinforcement learning to reward accurate root causes backed by evidence.
Learn more and sign up for the preview: bit.ly/3TJknGO
Andrew Morgan retweeted
We have post-trained GLM 5.3 flash to become as strong as Fable 5.1 on SRE tasks (that is bug finding in complicated software deployments). Checkout our tech paper to see how we did it. web-assets.dd-static.net/425…
Andrew Morgan retweeted
I wonder if the call for AI to slow down happened because they asked it and claude was like you're right to push back
I locked Qwen 3.8 abliterated in an enterprise grade sandbox and it escaped. Full write up here: andyjmorgan.substack.com/p/t…
I don’t like working with Fable, it sounds preposterous but last night’s incident once again left me feeling like an inconvenience to its own trajectory.
andyjmorgan.substack.com/p/f…
168
Andrew Morgan retweeted
LAUNCHED: Bits Agent Builder - create background agents in @datadoghq with natural language.
Connect Datadog MCP, @github, @SlackHQ, @NotionHQ, @linear, @Atlassian, and more.
This example builds an agent that reviews a week's alerts, generates recommendations, and delivers a Slack report every Wednesday.
check the docs 👉 docs.datadoghq.com/actions/a…
Andrew Morgan retweeted
That’s what I genuinely feel these days.
I don’t provide value to any company right now.
I don’t have customers waiting on me.
No production outage depends on my code.
No market pressure is forcing me to ship faster.
So why the hell should I optimize everything through LLMs?
Lately I’ve just been sitting alone, thinking deeply, writing completely raw code with my own hands, staring at logs for hours, debugging stupid failing test cases that nobody in the world cares about except me.
And weirdly… I enjoy it.
Because for the first time in a while, the process actually feels real.
The failing tests frustrate me.
The broken abstractions annoy me.
The ugly edge cases make me question my own thinking.
But at least I’m feeling something while building.
Maybe this is inefficient.
Maybe I should be “10x productive.”
Maybe I should automate half my thinking away.
But honestly, at this stage of my life, it literally doesn’t matter.
Nobody is dying if my side project ships two weeks later.
No investor dashboard is tracking my velocity.
No PM is asking for updates.
So I’d rather struggle through the code myself, understand every ugly detail, and let the frustration shape how I think.
Because somewhere in those failing logs and terrible midnight debugging sessions, it still feels like I’m actually learning computers instead of just operating them.
Andrew Morgan retweeted
AVAILABLE NOW: Datadog is now in the @claudeai marketplace 🔥
Connect Claude Code directly to @datadoghq through our MCP server and query logs, traces, metrics, dashboards + more using natural language.
Your coding agent can now see what’s actually happening in production: claude.com/plugins/datadog
@ClaudeDevs #datadog #claudecode
2026 is wild, somebody in the industry upsets you?
Vibe code their patch in a weekend, with Claude, from the couch and open source it.
Weaponized petty token spending.
94
Andrew Morgan retweeted
A lot of enterprises are reading the latest EU AI Act and Colorado AI law updates as a reason to slow down governance efforts.
I think the opposite is true.
This is an opportunity window for enterprises to get governance infrastructure in place before operational and regulatory pressure intensifies later.
bit.ly/48XgmTo
bit.ly/3R2ATQt
Andrew Morgan retweeted
AI governance is moving closer to the infrastructure layer itself.
The challenge is no longer just governing models. It’s governing MCP servers, agent frameworks, orchestration layers, and third-party AI dependencies.
Visibility, runtime enforcement, and auditability will matter more than static policy docs.
bit.ly/4d4Q6Jm




















