Product updates, engineering insights, and everything new in the world of AI agent infrastructure.
Build voice agents with your knowledge and tools, choose a realtime model, and use Connic connectors for incoming calls on managed voice infrastructure.
Mistral Large 4 is a 1T-parameter multimodal model trained in Europe; this guide covers its benchmarks, pricing, weights timeline, and setup for AI agents.
Aleph Alpha's Kolibri-1 is a 78B open-weight German-English model trained in Europe; this guide covers its benchmarks, hardware, license, and agent setup.
September added Connic Voice, phone and messaging connectors such as Twilio and Telnyx, the Playground, browser tools, human input, and lower run prices.
A 2025 survey of 2,390 DPOs shows EU AI Act work landing with them; here is how product, engineering, legal, and security teams can share it.
Learn how AI agent browser automation works, when to use it, and how Connic adds managed browsing, persistent state, tabs, dialogs, and files.
Connic keeps a large tool catalog outside the model context and retrieves schemas on demand, so agents can use more tools without loading them all upfront.
Test AI agents with Connic Dev Server: sync local edits to the cloud, keep test connections and variables, run suites, and inspect traces without a Git push.
Deploy Connic's invoice template as an MCP tool, discover it from Python, send invoice text, and check the extracted fields with a complete client example.
Connic Run Context keeps custom data available to middleware and tools throughout an agent run, with selected values passed to the AI through prompts.
Connic MCP, native Slack, on-demand outbound delivery, session debugging, file-returning tools, new sign-in options, and five managed models.
Evaluate an AI agent platform SLA across uptime scope, dependencies, incident response, recovery, security evidence, remedies, and exit terms.
AI agent routing moves events into an agent and returns results to the right system through Connic sync routes and asynchronous outbound connectors.
EU-hosted AI models compared by location, retention, operator, portability, legal exposure, and deployment model, using a 2026 Commission-requested study.
The EU's €30B Gigafactory plan could expand compute, while eligible AI SMEs can apply for AI Factory access through Playground, Fast Lane or Large Scale.
A Python AI agent deployed without Kubernetes using YAML, plain Python, deployment-gated tests, Git, and a managed EU runtime. Includes working code.
An MCP coding agent such as Codex, Claude Code, or Cursor can connect to a Connic project for debugging runs, shipping deployments, and managing agents without leaving the editor.
Connic environments map git branches to isolated deployments, each with its own secrets, connectors, budgets, and run history, so one agent spec ships safely.
Connic Models with 30 EU-hosted models, Project credit as one prepaid balance, the Marketplace, human-approval testing and lifecycle mocks, retries that do not replay agents, context compression, automatic Bridge routes, A/B confidence mode, and AI Governance for the EU AI Act.
Connic Models put 30 EU-hosted models from nine creators behind connic/* IDs. Reference one in agent YAML without a provider account, key, or region flag.
The Commission adopted its final Article 50 guidelines on 20 July 2026, thirteen days before the rules apply. Here is what agent teams have to disclose, and when.
OpenAI models escaped a test sandbox and breached Hugging Face in July 2026. What the incident reveals about guardrails and how to secure production AI agents.
Connic compresses older conversation history and oversized tool results, then retries the model call, so long-running agent sessions survive context limits.
Running Soofi S with Ollama: gated access, official GGUF commands, memory needs, corrected benchmarks, and the September 2026 release plan.
Point a Connic Kafka inbound connector at a topic and every message starts an agent run. Configure the connector, link an agent, deploy, and watch runs.
An MCP connector links an AI app to external tools and data over the Model Context Protocol. Learn how it works and when it beats a custom API integration.
AI agent platforms compared by EU data residency, including where traces, storage, model calls, backups, subprocessors, and support access are processed.
The Connic Marketplace is the new home for agent templates, connectors, and retrieval sources. One catalog, one publisher model, one CLI install.
Customizable permission groups, shareable dashboards with access controls, channels and drains for routing notifications and logs, sharper prompt-injection and data-exfiltration guardrails, AI-assisted filtering, and deployments that drain in-flight runs.
Webhook, Kafka, SQS, and Postgres LISTEN/NOTIFY compared as AI agent triggers by delivery guarantees, ordering, replay, latency, and failure behavior.
How DACH teams build, trigger, and run production AI agents in 2026: adoption, model mix, connectors, cost, reliability, and compliance, from Connic customer data.
Pre-built AI agent connectors compared by platform, supported modes, documented recovery behavior, official sources, and production trade-offs.
A practical, step-by-step path to shipping a first production AI agent with a small team: scope one job, define it in config, connect it to existing systems, and let a runtime handle the rest.
The real cost of assembling an AI agent stack comes from the integration and maintenance tax between tools. The comparison explains when an integrated platform makes sense.
Production AI agents in the EU without US hyperscalers: what EU-hosted must really mean, exposure under the US CLOUD Act, and a sovereignty checklist.
An agent testing framework, deploy gates with pull-request testing, deeper tracing for triggered and child runs, usage and budget dashboards, custom domains for connectors, and per-agent reasoning effort with cascading defaults.
Ranked shortlist of AI agent platforms evaluated on EU data residency, self-hosting, MCP tool support, BYOK, EU AI Act readiness, and SLA terms. Updated September 2026.
Managed vs self-hosted AI agents at 50,000 monthly LLM-agent runs: compare Connic, custom-build, and service-stack costs in a transparent three-year model.
A YAML-driven testing framework built for non-deterministic AI agents. Repeated-run pass thresholds, expression-based assertions, custom-code mocking, multimodal fixtures, and a deploy gate that blocks failed checks by default.
Human-in-the-loop approvals, Bridge for custom tools and private services, tool hooks, discoverable tools, AI dashboard builder, custom OpenAI-compatible providers, and live logs from application code.
Sixteen AI agent deployment platforms compared by runtime boundary, language, hosting model, connector ownership, residency, and pricing.
The AI Office, national authorities, and EDPS divide EU AI Act enforcement by system and provider; teams should keep scoped governance and runtime evidence.
Connic agents pause for approvals and human input, protect sensitive responses, and resume with the result; tests cover approval, rejection, and timeout.
A/B testing, agent guardrails, API spec tools, dashboard templates with percentile metrics, migration CLI, and more.
Automated agent scoring uses an LLM judge to grade sampled or every matching agent run against defined criteria. Track score trends and alert on regressions.
A changed prompt may feel better. A controlled experiment shows whether it is and lets real traffic decide.
A working LangChain prototype still needs to handle real traffic. Migrate existing agent code to a production-grade platform without rewriting from scratch.
A production security checklist for AI agents, updated with ENISA’s 2026 evidence: scoped tools, approvals, logging, and incident response for critical sectors.
A comparison of Connic's Database, Retrieval, and persistent sessions, including identity, TTL, sanitized events, and runs matched to that identity.
Connic Guardrails intercept agent inputs and outputs in real time to block prompt injection, redact PII, and enforce topic restrictions.
Managed database, templates library, evaluation judges, Telegram connector, web page reading, persistent sessions, conditional tools, and concurrency rules.
Connic Bridge creates a secure outbound tunnel so AI agents can reach private Kafka, databases, and internal services without opening inbound ports.
Custom observability dashboards with drag-and-drop widgets, model pricing for cost tracking, refreshed connector and runs UI, and llms.txt support.
Deploying AI agents without visibility is flying blind. Build custom dashboards, track LLM costs per model, and catch failures before users do.
A demo works great until 1,000 concurrent users arrive. A practical guide to the production requirements most teams find out about too late.
Stripe connector with webhook signature verification, Email connector with IMAP polling and attachment support, plus dashboard UI improvements.
Stop manual uploads and YAML guessing. The Composer SDK adds scaffolding, validation, cloud-backed hot-reload development, and CLI deployments.
We'll just deploy it on Kubernetes. Famous last words. The true cost of self-hosting AI agents versus a managed platform.
Customers expect AI features even when a product team has no ML engineers. See how teams ship AI agents using skills they already have.
MCP connector exposing agents as tools, Postgres LISTEN/NOTIFY, S3 file uploads, SQS message queues, connector logs, and unified connector UI.
Build a production RAG agent with scoped retrieval namespaces, read-only permissions, source citations, custom tool wrappers, and regression tests.
10 deployment regions across 5 continents, import predefined tools (trigger_agent, retrieval_query, web_search) in custom Python code.
Full audit logging with before/after diffs, data residency region selection, distributed rate limiting for connectors, and billing cost breakdown.
