# auxfirst Services > Canonical: https://auxfirst.com/#services > License: CC BY 4.0 · auxfirst agency 2026 auxfirst brings the rigour of UX/UI/CX agencies into the world of AI agents — helping product, developer, and leadership teams design, architect, and ship agentic systems that **earn trust and compound value**. The work is structured into three practices, each addressing one layer of the agentic stack, plus four engagement formats. ## The three practices ### 01 · Agentic API Experience — for app developers Design and build agent-first developer experiences — from tool-calling architecture to MCP integration and composable agent pipelines. - Agent infrastructure & framework design - Model Context Protocol (MCP) integration - Tool calling & function calling API design - Agent runtime environment architecture - CLI & developer-first AI tooling - Prompt & LLM orchestration layers - Memory systems (short & long-term) - API-to-agent interface patterns Detail: [agentic-api-experience.md](https://auxfirst.com/agentic-api-experience.md) ### 02 · AI Product Experience — for product teams Transform your SaaS from a static tool into an adaptive partner. We design the interaction paradigms, generative UI, and trust scaffolding that makes AI products defensible. - Conversational & natural language UX - Generative & adaptive UI design - Intent-driven & outcome-oriented UX - Proactive & predictive interaction design - Multimodal interaction patterns - Trust, transparency & explainability UX - Hallucination mitigation UX - Human-in-the-loop & escape hatch design Detail: [ai-product-experience.md](https://auxfirst.com/ai-product-experience.md) ### 03 · Agent Process Design — for business & GTM teams Design the best agents for your business processes — from GTM automation to revenue intelligence, workflow orchestration, and decision support. - GTM automation with AI agents - Revenue intelligence agent design - Workflow automation & orchestration - Decision intelligence systems - Semi-autonomous workflow design - Agent planning & task decomposition - Multi-agent system architecture - Control vs. autonomy balance mapping Detail: [agent-process-design.md](https://auxfirst.com/agent-process-design.md) ## Engagement formats Each engagement delivers clear decisions, tangible artefacts, and implementation-ready outputs. ### 01 · Executive Seminar Align leadership on what agentic systems actually mean for your product and business. A focused session for founders, executives, and product leaders to build a shared understanding of: - what "agentic" really implies beyond hype - how trust, memory, and autonomy reshape product design - where your current product or strategy stands - and what decisions need to be made next **Best for:** Leadership alignment, early-stage exploration, strategic resets. **You walk away with:** A shared mental model of Agentic Experience (AUX) · A clear view of risks, opportunities, and blind spots · Prioritised strategic directions · A decision framework for next steps. ### 02 · Team Workshop Turn abstract AI concepts into concrete product and design decisions. A hands-on working session with product, design, and engineering teams to translate agentic principles into your actual product context. We move from theory → application → decisions. **Best for:** Product teams preparing to design or redesign AI-powered features. **You walk away with:** Mapped user journeys for agent interactions · Defined trust patterns (confidence cues, escape hatches, human-in-the-loop) · Initial memory and context strategy · Aligned design principles across product, UX, and engineering. ### 03 · Agent Experience Audit Identify where your AI product breaks trust — and how to fix it. A structured diagnostic of your current product, assistant, or workflow using the AUX framework. We analyse how your system behaves across: - intent understanding - memory and context handling - transparency and explainability - control and fallback mechanisms **Best for:** Teams already shipping AI features or copilots whose adoption has stalled. **You walk away with:** A documented trust-gap inventory · Pattern-by-pattern recommendations · A prioritised remediation roadmap. ### 04 · Blueprint Sprint Three weeks. Single workflow. Both lenses framed (aggregate + individual). Walk out with the agent home mockup, the trust canvas, the storyboard, the runtime spec, and the build brief — everything engineering needs to start building Monday. ## Open source and supporting artefacts - **TrustKit** — open-source YAML schemas for heuristics, trust architecture, trust-gap taxonomy, agent specs, memory policies. MIT + CC BY 4.0. https://github.com/auxfirst/trustkit - **Trust Canvas** — free Figma artefact for mapping an agent's trust topology. https://www.figma.com/community/file/1635742721765886887 - **The 10 AUX Heuristics** — evaluation framework. [heuristics.md](https://auxfirst.com/heuristics.md) - **The 6 AUX Patterns** — interaction primitives. [patterns.md](https://auxfirst.com/patterns.md) - **The Trustworthy Agents ebook** — for ad and media agencies. https://auxfirst.com/trustworthy-agents-ebook.html ## Industries and domains auxfirst publishes specialised work for: - **Advertising and media** — ad holding companies, media agencies, brands, publishers, platforms. https://auxfirst.com/ad-industry/ - **Family offices and wealth operations** — bounded agents for governance, entities, advisors, liquidity. https://auxfirst.com/agentic-family-office.html - **Legacy SaaS** — retrofitting copilot-era products into agent-first ones without a rewrite. https://auxfirst.com/agent-first-design-legacy-saas-retrofits.html ## How to engage - Start a project: https://auxfirst.com/index.html#contact - Subscribe to the newsletter: https://auxfirst.substack.com/ - Read the canon: https://auxfirst.com/resources.html --- Related: [The AUX Manifesto](https://auxfirst.com/manifesto.md) · [The six AUX patterns](https://auxfirst.com/patterns.md) · [The ten AUX heuristics](https://auxfirst.com/heuristics.md)