Mat Keep

Product management and marketing. Advisor and consultant working on #AI, data, #developers. Ex #MongoDB, #MySQL, #Oracle, #Sun. Avid traveller and #Pompey fan

[Mat Keep @matkeep]

I’ve had worse starts to the week. Somewhere on the Med between the coasts of Spain and Morocco

[Oso @osoHQ]

With some help from @cyera_io, we finally measured how broken permissions are
https://t.co/W0G5mZCESm

[Mat Keep @matkeep]

What's not to love - #opensource and #AI. @RedHat turns to @ApacheAirflow and @astronomerio to deliver #agenticAI https://t.co/u8Cgk6tUJ7

[Mat Keep @matkeep]

The next data stack shift:
Old world → #ETL pipelines → dashboards
New world → #context pipelines → #AI agents
Models aren’t the bottleneck anymore. Context is.

The winners will build the AI context layer: https://t.co/45veLOXct7

[Mat Keep @matkeep]

If #AI #agents become the primary “users” of #databases, a lot changes: query patterns, isolation, ephemeral environments.

Interesting industry perspective. Keen to see how other database vendors approach this shift.
https://t.co/sGbZ5XSa8q

[Mat Keep @matkeep]

Visa-scale data orchestration

I put together a new Airflow in Action case study on how @Visa runs @ApacheAirflow for critical #Analytics and
data workflows, with a ready made #Context layer for #AI

https://t.co/PGcEVF6gaI

[Mat Keep @matkeep]

Feeling grateful for all of the kind and uplifting birthday messages I received this year…..well most of them anyway

[Mat Keep @matkeep]

If your #AIAgents can call tools, read data, or execute workflows…you’ve built an authorization problem.
I wrote a guide on preventing over-permissioned agents for my friends over at @osoHQ :

https://t.co/ggXMikfHVa

[Mat Keep @matkeep]

The team at @datadoghq processes 100+ trillion events per day. How do you orchestrate data workflows at that scale? In our latest @ApacheAirflow in Action case study, Datadog shares why they adopted #Airflow 3: https://t.co/6zwR2p4k62

[Mat Keep @matkeep]

Seeing @ApacheAirflow increasingly deployed as a shared platform across #Engineering teams.
Dag-level roles on @astronomerio add the missing piece: fine-grained access control so teams only see and operate the pipelines they own. https://t.co/02ciGQUpfw

[Mat Keep @matkeep]

How #SoftwareEngineering is evolving in face of #AgenticAI. Specs should be equations, not essays. Precision wins over prose when AI writes code. Also addresses risk of "cognitive debt"
https://t.co/KX22fQ21rW

[Mat Keep @matkeep]

Left #MongoDB thinking CAP theorem was behind me. #Agents pulled me right back in: Capability, Autonomy, Permissions: pick 2.
The difference: CAP is physics. The agent version is an infrastructure problem and these are solvable - the @osoHQ take
https://t.co/3HxFntbU3C

[Mat Keep @matkeep]

Nearly 50% of #AI #agentic usage today is in #softwareengineering. The other half? Fragmented across 16+ industries with most under 5% each. Coding may be saturated. Vertical AI agents are the wide-open frontier. https://t.co/Yva4GytgW2

[Graham Neray @grahamneray]

We made an implicit bargain with overpermissioning: bad, but not bad enough to fix. It worked because humans sleep, work business hours, slow down.
Agents have no remorse and no speed limit. The bargain is over.

https://t.co/5wmZTGZMOY

[Mat Keep @matkeep]

"Cognitive debt" is gaining traction. Fueled by #vibecoding it slows teams down more than #techdebt, accumulating when assumptions aren’t documented and context is lost. Product Requirement and Design Decisions docs have never been more important! https://t.co/mRaWbTmttA

[Mat Keep @matkeep]

Always wanted to write a case study about #Oracle - and now I can! How they use @ApacheAirflow to orchestrate #AI pipelines across clusters of scarce #GPUs https://t.co/aCJIJFRWfX

[Mat Keep @matkeep]

Looks like #Claude Sonnet 4.6 is a serious step up in long-context reasoning, and agent workflows, especially with the 1M token window. Looking forward to trying it out to see how it holds up on real projects. https://t.co/vrvHXxaVHQ

[Mat Keep @matkeep]

Conjecture that #AIAgents may drive new #programming languages designed for clarity and agent reasoning. With code cost falling, languages with explicit structure and simpler tooling could outcompete old ones. https://t.co/3RJQGnkG52

[Mat Keep @matkeep]

Team at #Microsoft warns of “#AI Recommendation Poisoning”: hidden prompt injection in AI summarize, skewing future recommendations without users knowing. Security must evolve with #agents. This is why I'm excited to be working with @osoHQ
https://t.co/8zIK2HBU1P

[Mat Keep @matkeep]

Interesting post - #Java is winning production #AI: 62% of enterprises now run AI apps on Java. #Python still dominates research and prototyping, but the claim is Java leads where scale, security, and uptime matter: https://t.co/xcE6E1MV9r