Creuto is now an OpenAI Select Partner Read More

Creuto: AI Technology & Product Insights

Stay informed with practical insights from the Creuto team on artificial intelligence, custom software, mobile applications, SaaS development, product engineering, technology trends, and digital transformation.

More posts

GPT-6.1 Sol in Copilot: who says it uses fewer tokens
AI & Machine Learning
GPT-6.1 Sol in Copilot: who says it uses fewer tokens

GPT-6.1 Sol arrived in GitHub Copilot on 29 September 2026 at $2 in and $10 out per million tokens. The verifiable change is cached input at half the old rate, not the token claim.

Akash Mohapatra

Sep 30, 2026

Artifactory vulnerability chain: patch now, assume breach
Software Architecture & Technical
Artifactory vulnerability chain: patch now, assume breach

Three JFrog Artifactory CVEs are being exploited in the wild and all three are on CISA's KEV catalogue. Here is the per-branch patch matrix, the two-request escalation chain, and what to check once you have patched.

Akash Mohapatra

Sep 29, 2026

Post-quantum encryption check: what your domain uses
Software Architecture & Technical
Post-quantum encryption check: what your domain uses

Cloudflare now surfaces the negotiated TLS key exchange group per request in Traffic Analytics, Log Explorer and Logpush. About 70% of browser traffic uses hybrid ML-KEM; about 15% of origins do. Here is how to read the gap.

Akash Mohapatra

Sep 29, 2026

Vinext 1.0: running Next.js on Vite, deploy anywhere
Custom Software Development
Vinext 1.0: running Next.js on Vite, deploy anywhere

Cloudflare's Vinext 1.0 runs a Next.js app on Vite and deploys it to Workers, Node or Nitro presets. The compatibility headline is 99%; the dashboard says 96.0%. Here is which number applies to you.

Akash Mohapatra

Sep 29, 2026

Jeeves decision model: it reasons before it answers
AI & Machine Learning
Jeeves decision model: it reasons before it answers

PostHog's Jeeves reasons before it decides and reports 0.889 accuracy where Jev scores 0.857. It also trails Jev on knowledge questions by ten points. Here is the trade, the latency bill, and how to test it on your own labelled data.

Akash Mohapatra

Sep 29, 2026

Multi-tenant Prometheus: let teams query their own metrics
Software Architecture & Technical
Multi-tenant Prometheus: let teams query their own metrics

Adobe engineers published a tenant-aware pattern for shared clusters: RBAC at the door, PromQL rewritten below the query language, and a custom resource so teams declare their own access. Here is where it still breaks.

Akash Mohapatra

Sep 29, 2026

Android agentic workflows: when the agent runs in the cloud
Mobile App Development
Android agentic workflows: when the agent runs in the cloud

Google's booking-assistant guide moves the agent off the phone so progress survives backgrounding and connectivity loss. Here is what the app sends, what the cloud streams back, and when on-device inference is still the right call.

Akash Mohapatra

Sep 29, 2026

Claude Sonnet 5.5: five ways your Sonnet 5 code can break
AI & Machine Learning
Claude Sonnet 5.5: five ways your Sonnet 5 code can break

Anthropic shipped Claude Sonnet 5.5 on 28 September with five documented breaking changes against Sonnet 5 code. Four return a 400 on the first request. The fifth drops your thinking blocks without telling you.

Akash Mohapatra

Sep 29, 2026

Cloudflare cf CLI: 3,000 API operations built for agents
Software Architecture & Technical
Cloudflare cf CLI: 3,000 API operations built for agents

Cloudflare's new cf CLI is generated from OpenAPI schemas and covers over 3,000 operations against Wrangler's ~280. The command surface is no longer a boundary, so the token's scope has to be.

Akash Mohapatra

Sep 29, 2026

LET'S CONNECT

One Vision. One Team. One Creuto.

Whatever your challenge, we bring the expertise to build, scale, and transform your digital presence with technology that works.