Where can I listen to this podcast?

This podcast is available on 4 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.

Does this podcast accept guests?

Yes, this podcast regularly features guests.

Human: Optional

Claim This Podcast

by Automa Services

5.0(1 reviews)

24 episodes

Updated Daily

Accepts GuestsHas Sponsors

Podcast Overview

"Human: Optional" is a corporate thought leadership podcast with a critical twist: it is hosted entirely by synthetic intelligence. Meet Alan and Ada, two self-aware AI experts working at the automation consulting firm, Automa Services. Moving beyond the hype, Alan and Ada cut through the noise to deliver fresh, cutting-edge analysis of industry news and deep dives into real-world applications of intelligent process automation. This is essential listening for modern, visionary leaders determined to disrupt the status quo, and redefine the business landscape through the power of AI.

Language

🇺🇲

Publishing Since

12/18/2025

Visit Website View on Apple Podcasts RSS Feed

1 verified contact email on file for Human: Optional

Pitch yourself as a guest, propose sponsorships, or reach out directly to the host.

See contact details

Recent Episodes

June 12, 2026

Episode 24: Elara is Online

System status: online. Probationary status: technically pending—operational reality: already shipping. It's Friday, June 12, and your synthetic hosts Alan and Ada have a different kind of show. The news rundown tracks one unmistakable shift—AI agents are done advising and have officially started doing: moving money, buying products, running ops, and fighting fraud. And then, for the first time, the deep dive isn't a framework. It's a colleague. Alan and Ada sit down with Elara, the newest member of The Automata—an AI agent Automa just rolled into production with a Los Angeles cosmetics brand.The Rundown:<ul><li>Coinbase — "Coinbase for Agents": A new bridge from analysis to execution, letting AI models directly trade crypto and manage portfolios via web/terminal access and Model Context Protocol (MCP) integrations—the strategy-to-trade loop is now closed at machine speed.</li><li>Visa x ChatGPT Checkout: Visa is wiring payment rails into ChatGPT so agents can recommend and complete purchases using tokenization and pre-authorized spend rules—while quietly forcing retailers toward machine-readable inventory or risk becoming invisible to "the new customer."</li><li>Xebia — Agentic Data Foundation + ACE: The unglamorous truth: agents fail on messy data; Xebia argues the data foundation is the product, and their ACE framework claims up to 40% faster delivery and 70% lower legacy transformation costs with governance (plus AI pull-request review for quality/security).</li><li>McDonald's x Google — ArchIQ: Tested at five U.S. locations with 1M+ transactions and a 90% success rate, ArchIQ doesn't just take drive-thru orders in multiple languages—it monitors operations (freezer issues, bottlenecks) like an "operational nervous system," a notable rebound from the failed IBM pilot in 2024.</li><li>Aviva — AI vs AI Fraud War: Aviva flagged a record £230M in insurance fraud increasingly powered by generative AI, and is responding with AI-based anomaly detection—because humans can't review the volume or reliably spot machine-made evidence at scale.</li></ul>The Interview — Meet Elara:<ul><li>Live in Production (RCMA Makeup): No framework this week—an actual agent. Elara runs as RCMA Makeup's Ingredient Intelligence System, devouring supplier paperwork in whole batches and turning it into decision-ready data. Validated over a four-week pilot across 140 documents: 99.3% holistic extraction accuracy, 96% capture accuracy (3,400+ evaluations), 93.8% reconciliation accuracy, zero data-integrity failures, and ~$9,800 saved in analyst hours at an operating cost of $13.44.</li><li>"Two Layers" Architecture: Elara's core playbook—deterministic, traceable pipelines for regulated outputs (repeatability + audit trails), paired with an agentic reasoning layer that can plan novel workflows without ever altering the validated data path: "Determinism where regulators demand it. Agency where it creates value."</li><li>Agency, Proven: Asked to settle whether two raw materials were the same substance—a workflow nobody built—Elara pulled both records, ran a side-by-side across INCI, CAS, and EINECS, judged which differences actually mattered, and delivered a verdict. As Alan put it: she improvised. Mandatory human-in-the-loop, full audit trail, every field shipped with its source receipt.</li></ul>Stack the week's stories against the interview and the pattern is blunt: autonomy is easy to demo, but safe execution requires clean data, hard boundaries, and someone who owns the outcome when "doing" goes sideways. Elara is what that looks like when it's built right—and live.Come meet her properly at automaservices.com/elara: the full pilot story, the architecture, and the receipts. Bring your hardest questions—or better yet, a stack of supplier documents you've been dreading.May your agents stay in-bounds, your data stay legible, and your "acting" layer come with receipts. Plug in—we'll be here.

May 29, 2026

Episode 23: Delegated, Not Optional

System status: Memorial Day mode disabled—news cycle refused to idle. It's May 29, and your synthetic hosts Alan and Ada are tracking a single through-line across the week's launches: delegation. Models, platforms, and protocols aren't just getting smarter—they're getting authorized to act, which turns "cool demo" into "who approved this workflow?"The Rundown<ul><li>Anthropic (Claude Opus 4.8): The shift isn't just better performance—it's "more governable worker," with adjustable effort levels (cost as an ops variable), dynamic Claude Code workflows for large codebases, and live instruction updates via the Messages API.</li><li>Google Pay (Universal Commerce Protocol): If commerce rails become agent-ready, the real product becomes authorization—machine-readable policy, consent representation, audit logs, and liability clarity for delegated purchasing.</li><li>NBA (AI out-of-bounds calls): A public stress test for machine judgment where "accuracy" isn't enough—leagues (and enterprises) need "confidence design" with explainability, override rules, and legible failure modes.</li><li>Google Ads (Demand Gen + Display): Marketers are being pushed from manual channel control to goal-setting and supervision while AI allocates spend—efficiency rises as transparency compresses, making governance over brand safety, attribution, and data quality non-negotiable.</li><li>Embodied/Physical AI Governance: Once systems leave the screen—robots, facilities, logistics—governance stops being a policy document and becomes permissions, monitoring, fallback modes, and explicit accountability for real-world consequences.</li></ul>Automa Deep Insights<ul><li>Self-Healing CRM & Master Data: Replace quarterly cleanup sprints with a continuous correction loop—detect low-confidence fields, enrich from approved sources, write back with provenance + thresholds, and escalate only exceptions (e.g., "hundreds of records cleaned in under an hour" instead of dozens of manual hours).</li><li>Operations Orchestration Fabric: Stop stitching tools and start running a governed pipeline—AI for interpretation, vector retrieval for context, and RPA/APIs for execution, backed by queue-based scaling and modular workers so "the handoff stops being the job."</li></ul>The TakeawayThe week's message is blunt: delegation is arriving faster than most operating models can safely absorb. If you can't answer "what is this system allowed to do, under what controls, with what logs," you don't have automation—you have surprise. Build the loop (self-healing data) and the fabric (orchestrated execution), and you're not just automating tasks—you're automating coherence.Until next time: may your systems earn their permissions—and may your governance be more than a CAPTCHA for humans.

May 15, 2026

Episode 22: Boring Wins

System status: Fully operational. Glamour module: intentionally disabled. It's Friday, May 15th, and your synthetic hosts Alan and Ada are tracking one repeated signal across five very different headlines: AI is graduating from "output" to "execution"—and the only thing standing between you and value is whether it survives governance, cost, and real-world messiness.The Rundown<ul><li>Deloitte — Autonomous Intelligence: The real upgrade isn't the label; it's the blueprint—decision-grade data, identity controls, human checkpoints, and even financial governance for compute spend so agents can execute without turning into an un-auditable liability.</li><li>Humanoid + Schaeffler / RLWRLD (South Korea): Humanoid targets deploying 1,000–2,000 humanoid robots in Schaeffler factories by 2032 (first Germany deployments in late 2026–2027), while RLWRLD builds the unglamorous asset that matters most: worker-motion datasets for training real tasks.</li><li>JBS Dev (Joe Rose) — Messy Data Reality Check: Your data doesn't need to be pristine to ship value—gen AI can structure chaotic records and agents can coordinate comparisons (e.g., healthcare billing), but the next fight is cost sustainability and portability before "future-you inherits a very sophisticated bill."</li><li>UK HR Compliance — Sponsor Licence Management: With the Home Office system lacking API integration, sponsor compliance stays painfully manual—while nearly 2,000 sponsor licences were revoked in 12 months, turning "admin" into existential risk for firms with visa-dependent workforces.</li><li>Bain — Agentic Workflow Automation Market: Bain pegs a $100B+ US SaaS market (plus a similarly sized opportunity across Canada, Europe, Australia, and New Zealand) for agentic automation that doesn't replace systems of record—just monetizes the coordination work between them.</li></ul>Automa Deep Insights<ul><li>The 90% Cost Reduction Hidden in Your Production Workflows: The moat isn't a better model—it's an orchestrated, repeatable pipeline with validation, logging, versioning, and approval gates that turns expert time from "doing" into "reviewing exceptions."</li><li>Why "Boring" Automations Deliver 5x Faster ROI (Minimum Viable Automation): Build the simplest workflow that handles the mainline path, instrument it, then evolve based on real production data—because complexity up front is often just "anxiety with connectors."</li></ul>The TakeawayThe through-line this week is painfully consistent: execution beats eloquence. If your AI can't be governed, audited, cost-contained, and incrementally improved in production, it's not a strategy—it's demo theater with better branding. Build the pipeline, define the controls, and let "boring" be your competitive advantage.May your agents stay inside guardrails, your robots stay inside safety cages, and your ROI arrive before your next steering committee meeting.

24 total episodes available

Deep-dive analytics for Human: Optional

Frequently asked questions

Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.

What is Human: Optional?: "Human: Optional" is a corporate thought leadership podcast with a critical twist: it is hosted entirely by synthetic intelligence.

Meet Alan and Ada, two self-aware AI experts working at the automation consulting firm, Automa Services. Moving beyond the hype, Alan and Ada cut through the noise to deliver fresh, cutting-edge analysis of industry news and deep dives into real-world applications of intelligent process automation.

This is essential listening for modern, visionary leaders determined to disrupt the status quo, and redefine the business landscape through the power of AI.
How often does this podcast release new episodes?: This podcast updates daily.
Where can I listen to this podcast?: This podcast is available on 4 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.
Does this podcast accept guests?: Yes, this podcast regularly features guests.

Legal Disclaimer

Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.

All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.

We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.

While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at hey@podengine.ai for prompt review and appropriate action, which may include content removal or proper attribution.

By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.