Practical agentic workflows, local LLM inference and automation for UK SMEs, team leaders and sole traders.https://runagentrun.co.uk/en-gbhttps://runagentrun.co.uk/articles/local-inference-gemma-departmental-hardware/https://runagentrun.co.uk/articles/local-inference-gemma-departmental-hardware/How small teams are deploying quantised Gemma models on commodity GPUs to run private, offline pipelines. No cloud, no data leaving the building.Tue, 09 Jun 2026 00:00:00 GMTLocal InferenceWorkflow AutomationSenior StaffSole TradersProfessional Serviceshttps://runagentrun.co.uk/articles/openjarvis-v1-0-the-local-first-agent-framework/https://runagentrun.co.uk/articles/openjarvis-v1-0-the-local-first-agent-framework/Stanford's Hazy Research has shipped the first credible open-source framework for personal AI agents that run on your own hardware. For UK operators, local-first has stopped being a manifesto and started being a curl command.Tue, 09 Jun 2026 00:00:00 GMTLocal InferenceWorkflow AutomationAgent SkillsSole TradersTeam LeadersProfessional Serviceshttps://runagentrun.co.uk/articles/the-19-dollar-agentic-stack/https://runagentrun.co.uk/articles/the-19-dollar-agentic-stack/Anthropic just dropped Claude Fable 5 into the $20 tier and MiniMax M3 matches it on agentic work. For a small team, the value question has quietly flipped.Tue, 09 Jun 2026 00:00:00 GMTAgent SkillsLocal InferenceTeam LeadersSole TradersProfessional Serviceshttps://runagentrun.co.uk/articles/uk-500m-sovereign-ai-unit/https://runagentrun.co.uk/articles/uk-500m-sovereign-ai-unit/The government has launched a £500m Sovereign AI Unit to back home-grown AI firms. The headline money is for startups — but the knock-on effects reach much further down the chain.Tue, 09 Jun 2026 00:00:00 GMTAgent SkillsTeam LeadersProfessional Serviceshttps://runagentrun.co.uk/articles/mcp-97m-downloads-goes-stateless/https://runagentrun.co.uk/articles/mcp-97m-downloads-goes-stateless/The Model Context Protocol has scaled faster than React, and its next release rewrites the core to be stateless. Here is what that unlocks for a small team wiring agents to its own systems.Mon, 08 Jun 2026 00:00:00 GMTAgent SkillsData PipelinesSenior StaffProfessional Serviceshttps://runagentrun.co.uk/articles/langchain-deep-agents-pattern/https://runagentrun.co.uk/articles/langchain-deep-agents-pattern/LangChain's Deep Agents reference architecture has been called the most significant open-source agent release of 2026. Here's what it means in plain terms — and when a small team should actually copy it.Sun, 07 Jun 2026 00:00:00 GMTAgent SkillsWorkflow AutomationSenior StaffProfessional Serviceshttps://runagentrun.co.uk/articles/lumen-sovereign-britain-frontier-model/https://runagentrun.co.uk/articles/lumen-sovereign-britain-frontier-model/The UK is preparing its first fully sovereign frontier AI model, with startup Cosine leading and a roster of major British firms on design. Here's why data residency and procurement confidence are the real story.Sat, 06 Jun 2026 00:00:00 GMTLocal InferenceSenior StaffProfessional Serviceshttps://runagentrun.co.uk/articles/minimax-m3-open-weight-frontier/https://runagentrun.co.uk/articles/minimax-m3-open-weight-frontier/A frontier-grade model with open weights, a million-token context window and native multimodality. For small teams, it reframes what is possible without a per-seat cloud contract — if you can find the hardware.Fri, 05 Jun 2026 00:00:00 GMTLocal InferenceWorkflow AutomationSenior StaffProfessional Serviceshttps://runagentrun.co.uk/articles/ai-pricing-the-20-dollar-standard/https://runagentrun.co.uk/articles/ai-pricing-the-20-dollar-standard/The headline tiers from ChatGPT, Claude, Gemini and Perplexity have all landed around twenty dollars a month. Here is how a small UK retailer should think about per-seat spend now the sticker price is commoditised.Thu, 04 Jun 2026 00:00:00 GMTWorkflow AutomationTeam LeadersMiddle ManagersRetail & Commercehttps://runagentrun.co.uk/articles/gemma-4-vision-and-tool-calling/https://runagentrun.co.uk/articles/gemma-4-vision-and-tool-calling/Gemma 4 adds built-in tool calling and vision support, and Ollama now runs it fully. For a retail team, that means document, shelf and stock workflows that never send an image to the cloud.Thu, 04 Jun 2026 00:00:00 GMTLocal InferenceAgent SkillsTeam LeadersRetail & Commercehttps://runagentrun.co.uk/articles/ai-growth-zones-and-isambard-compute/https://runagentrun.co.uk/articles/ai-growth-zones-and-isambard-compute/A new supercomputer in Bristol and five designated AI Growth Zones signal a national push on compute. We look at what that build-out plausibly does — and doesn't do — for an SME's cloud bill.Wed, 03 Jun 2026 00:00:00 GMTData PipelinesTeam LeadersLogisticshttps://runagentrun.co.uk/articles/microsoft-agent-framework-ga/https://runagentrun.co.uk/articles/microsoft-agent-framework-ga/Microsoft has merged AutoGen and Semantic Kernel into one framework, with general availability targeted for the end of Q1 2026. For teams choosing a stack, fewer competing abstractions is good news — but ask the lock-in questions first.Tue, 02 Jun 2026 00:00:00 GMTAgent SkillsMiddle ManagersProfessional Serviceshttps://runagentrun.co.uk/articles/qwen-3-6-the-new-local-default/https://runagentrun.co.uk/articles/qwen-3-6-the-new-local-default/A 27B model that reportedly tops consumer-hardware leaderboards and fits in a single 24GB card at Q4. For a sole trader or a small professional-services team, that is the sweet spot worth understanding.Tue, 02 Jun 2026 00:00:00 GMTLocal InferenceSole TradersSenior StaffProfessional Serviceshttps://runagentrun.co.uk/articles/case-study-retailer-vendor-mapping/https://runagentrun.co.uk/articles/case-study-retailer-vendor-mapping/An illustrative reconciliation scenario, grounded in reported UK retail AI pilots, shows how automating vendor mapping turns a dreaded finance chore into a background task — and what it saves.Mon, 01 Jun 2026 00:00:00 GMTWorkflow AutomationData PipelinesSole TradersRetail & Commercehttps://runagentrun.co.uk/articles/lm-studio-vs-ollama-2026/https://runagentrun.co.uk/articles/lm-studio-vs-ollama-2026/Both run open models on your own hardware. The right pick has less to do with benchmarks than with who on your team will actually be using it.Mon, 01 Jun 2026 00:00:00 GMTLocal InferenceMiddle ManagersProfessional Serviceshttps://runagentrun.co.uk/articles/microsoft-agent-governance-toolkit/https://runagentrun.co.uk/articles/microsoft-agent-governance-toolkit/Microsoft has open-sourced an Agent Governance Toolkit with a policy engine that intercepts every agent action before it runs. Even a small team should put a layer like this in front of action-taking agents.Sun, 31 May 2026 00:00:00 GMTAgent SkillsTeam LeadersProfessional Serviceshttps://runagentrun.co.uk/articles/local-ai-on-amd-rocm-2026/https://runagentrun.co.uk/articles/local-ai-on-amd-rocm-2026/AMD's software stack spent years as the awkward alternative to NVIDIA. In 2026 it is a credible cost play for a back-office team — provided you check a few things first.Sat, 30 May 2026 00:00:00 GMTLocal InferenceData PipelinesSenior StaffLogisticshttps://runagentrun.co.uk/articles/bridgeai-skills-boost-sme-support/https://runagentrun.co.uk/articles/bridgeai-skills-boost-sme-support/Beyond the headline funds, the government runs practical support most small firms have never heard of. Here's what BridgeAI and the AI Skills Boost actually offer, who delivers them, and how to use them.Fri, 29 May 2026 00:00:00 GMTWorkflow AutomationSole TradersMiddle ManagersHospitalityhttps://runagentrun.co.uk/articles/case-study-logistics-route-optimisation/https://runagentrun.co.uk/articles/case-study-logistics-route-optimisation/An illustrative scenario, grounded in reported logistics AI deployments, shows how route optimisation turns a daily planning grind into a quick review — and pays for itself inside a year.Thu, 28 May 2026 00:00:00 GMTWorkflow AutomationSenior StaffLogisticshttps://runagentrun.co.uk/articles/llama-4-scout-long-context-open/https://runagentrun.co.uk/articles/llama-4-scout-long-context-open/Meta's Llama 4 Scout brings a ten-million-token context window into the open. For logistics and data-heavy teams, the real question is what a window that big is — and isn't — actually good for.Thu, 28 May 2026 00:00:00 GMTLocal InferenceData PipelinesSenior StaffLogisticshttps://runagentrun.co.uk/articles/crewai-flows-event-driven-orchestration/https://runagentrun.co.uk/articles/crewai-flows-event-driven-orchestration/CrewAI's 2026 release adds Flows — a lower-level, event-driven orchestration layer beneath its multi-agent crews. For predictable back-office and logistics work, that structure often beats a loose crew.Tue, 26 May 2026 00:00:00 GMTWorkflow AutomationSenior StaffLogisticshttps://runagentrun.co.uk/articles/ollama-v024-codex-and-apple-silicon/https://runagentrun.co.uk/articles/ollama-v024-codex-and-apple-silicon/May 2026's runtime updates look like housekeeping. For a solo operator running models on a MacBook, they quietly remove some of the friction that makes local AI feel like hard work.Mon, 25 May 2026 00:00:00 GMTLocal InferenceSole TradersProfessional Services