# KBOps > By David Bingham · https://studiobing.com/davidbingham/work/kb-ops/ > Work by David Bingham. In 2022 at Beyond.ai I designed the product that shipped in March 2024 as KBOps: a system for capturing an expert's operational rules as testable concepts that watch streaming data and trigger notifications and actions. I sketched the rule builder and backtesting in February, wrote the operational model primer in March, ran the internal vision workshop in Glendale in July that aligned the company on its users, the service journey and the roadmap, and then carried the design through information architecture, a service flowchart, wireframes and six hi-fi screens by November. The work was designed under the name Advanced Alerting; Beyond Limits released it as KBOps, the knowledge component of its Hybrid AI Platform. - **Role:** VP Product Design - **Period:** 2022 - **Client:** Beyond.ai ## KBOps Block `kb-ops/opener` · https://studiobing.com/davidbingham/work/kb-ops/#opener A replica Mars rover in the lobby of Beyond.ai in Glendale, where this work was done. I open with the building because the project is the record of one year inside it, from a first sketch to a product the company agreed on. - Image: A replica Mars rover on a round gray rug in the Beyond.ai lobby in Glendale. Advanced AI for organic knowledge base management. ## Goals Block `kb-ops/goals` · https://studiobing.com/davidbingham/work/kb-ops/#goals The goals and the two-day agenda for the Glendale workshop in my hand, with the sticky-note legend beside them. The sequence is deliberate: users before journey, journey before MVP, MVP before assignments. The third goal, seeding material for the functional teams, is what made it a working session rather than an offsite. Beside the board, the room at work on the first and second days: colleagues writing stickies at the wall, then the group reading the journey back together, with the tripod and a laptop on a video call in shot. - Image: Whiteboard in blue marker with three numbered goals, the Tuesday and Wednesday agendas with small drawings, and a legend of colored sticky notes. - Image: Two colleagues at a white wall placing pink sticky notes, a third at a table, a camera on a tripod and a laptop on a video call. - Image: A group standing before a wall of pink and purple sticky notes while one of them points at it. Data scientists, designers, product team members, and company leadership gathered in Glendale for a multi-day workshop to outline an ambitious program around knowledge management. The product goal was to operationalize Beyond.ai's advanced AI technologies with industrial domain expertise. I orchestrated this session with an agenda of co-creation activities to extract differing views and bring them into alignment across a desired customer journey. We surfaced key engagement points with users of the system and built out a multi-stage research and development roadmap. ## Concept Block `kb-ops/concept` · https://studiobing.com/davidbingham/work/kb-ops/#concept The Advanced Alerting concept in one picture, drawn on the first day: a real-time data stream and an expert's rules go into a knowledge base that holds when, what value and what to do, and come out as a notification or an action. - Image: Whiteboard diagram in blue marker headed AA: a real-time data stream and rules by expert enter a box of when, value and what to do, leaving as notification and action. Our activities included persona definitions and situating those personas into our desired customer journey across sales engagement, contracting, on-boarding, operations, issue management, and tracking performance outcomes. With a majority of technical minds, we ran future-facing and empathy inducing activities like newspaper headline creation. Note: You will see this work referred to as both “KBOps” (knowledge base operations) and “AA” (advanced alerting). These were two product teams converging at this moment. ## Boards Block `kb-ops/boards` · https://studiobing.com/davidbingham/work/kb-ops/#boards Three boards from the workshop: human and computer decision making plotted over time, from experts training the system to the masses using it, and two future press releases the room filled in during the vision warm-up. Writing the launch story first forces the value claim into a sentence before a feature list can hide it, and one of the sheets is the earliest place the name KBOps appears. - Image: Whiteboard diagram in purple marker headed Human-Computing Decision Making, plotting experts and the masses against time toward optimized human decision making. - Image: A press-release template filled in red ink with a healthcare headline, a quote naming KBOps and a sidebar of four points. - Image: A press-release template filled in blue ink with the headline BL builds a society of the minds and a sidebar of nine points. ## Blueprint detail Block `kb-ops/blueprint-detail` · https://studiobing.com/davidbingham/work/kb-ops/#blueprint-detail The service journey wall in three framings: the sales and setup stretch with its actor lanes, the middle span marked smart factory with the transition chain above it, and the operational end from procedures taken through outcome validation to offboarding. At this distance the stickies read and the lanes show who does what at each stage. - Image: Left end of the blueprint wall: the commercial and sales lane, a Pay Us line, and sticky notes from describing the problem to install and config. - Image: Middle of the blueprint wall: the smart factory span, feature and model design stickies, and the blue transition chain rising to a customer center of excellence. - Image: Right end of the blueprint wall: an orange operator figure and stickies from send recommended procedures through outcome validation to offboarding. ## Roadmap Block `kb-ops/roadmap` · https://studiobing.com/davidbingham/work/kb-ops/#roadmap The release ladder in my hand on the second evening. Each horizon is defined by the question it answers and who asks it: the expert at six months, operators at twelve, the business owner at eighteen. The same board carries the capability staircase and the three target accounts, one of which took me to Houston four weeks later. 1. V1 – 6mo: Prove the tech. Can KB reduce my downtime? Identify early adopter customers, talk to sales/CoE teams and alpha partners. Get error codes, IT topologies — devices? networks? restrictions? 2. V2 – 12mo: Scale and operate. Can this scale + learn? Deeper engagement with operators and experts. 3. V3 – 18mo: Improve and deliver. Can we do this in real-time? Ensure business owner is satisfied with resulting metrics and system performance. - Image: Whiteboard with a staircase of pink stickies, the Cyrus framework list, a triangle of three questions and the V0 to V3 ladder. ## Journey Block `kb-ops/journey` · https://studiobing.com/davidbingham/work/kb-ops/#journey The July wall synthesized in December as a matrix: three customer tiers over an eleven-stage user journey, from learning about the offering to refining knowledge. The target accounts, the dates and a colleague's framework were stripped out; what stayed is the structure. It names KBOps as the product. - Image: A wide matrix: a triangle of three customer tiers, v1 to v3, beside rows of text over an eleven-stage user journey from learn about offering to add and refine knowledge, with figures for each stage and a Sales, Setup and Operation band beneath. *Workshop whiteboard journey was synthesized into a clean map and shared broadly.* ## Houston Block `kb-ops/houston` · https://studiobing.com/davidbingham/work/kb-ops/#houston Four weeks after bp Wind went on the Glendale wall as a target account, I was in Houston for two days of customer discovery. That engagement is its own project; it is cited here because it is where the product defined in July met its first real users. - **bp-wind** — bp Wind — Soon after our workshop, the team flew to Houston to engage with bp's wind energy business. I defined the workshop agenda and goals to understand bp's use-case and alignment to our proposed KBOps ecosystem. Validating with monitoring experts in the context of their turbine control room helped refine the model and move us forward into greater design detail. - Image: A wind operations control room: a wall of screens with charts and a map of the United States above a curved desk of monitors, an operator at work. ## Site visit Block `kb-ops/site-visit` · https://studiobing.com/davidbingham/work/kb-ops/#site-visit From the visit: wind turbine blade sections on the wall, the agenda and sticky notes at the whiteboard, and the opportunity drawn as a sum, megawatt-hours times downtime times the price of generation, plus the value of the service agreement. - Image: Three wind turbine blade cross-sections mounted on a green wall beside a caption panel. - Image: A woman stands at a whiteboard with an agenda written in marker and columns of pink sticky notes. - Image: A whiteboard drawing of a wind turbine beside Calculate opportunity: MWh × downtime × generation $ (varies) + value of SLA × MWh. ## Roles Block `kb-ops/roles` · https://studiobing.com/davidbingham/work/kb-ops/#roles The roles of a wind operation drawn on the whiteboard, beside the customer's priorities in a column of sticky notes: the operator on a shift monitoring nine sites and a thousand turbines, the remote technician, the operations center manager, the data scientist, the site and field crews, the performance manager and the auditor. - Image: A whiteboard of roles drawn as stick figures with notes: operator, remote technician, ROC manager, data scientist, site and field, performance manager and audit. — The personas working within & around bp Wind's remote operations center (ROC). - Image: A tall whiteboard strip of pink sticky notes ranked under Higher priority, with arrows to either side. — Desired business performance outcomes. ## Service boards Block `kb-ops/service-boards` · https://studiobing.com/davidbingham/work/kb-ops/#service-boards The service journey mapped with the customer on two whiteboards: blue, orange and green sticky notes along lines and loops of arrows, with a list of what comes next. - Image: A narrow whiteboard with blue, orange and green sticky notes along drawn lines and arrows. - Image: A whiteboard with blue sticky notes along the top, orange and green notes below on loops of arrows, and a list headed Next. *The bp Wind ROC ecosystem map.* ## Wind maintenance Block `kb-ops/wind-maintenance` · https://studiobing.com/davidbingham/work/kb-ops/#wind-maintenance What the visit produced: a knowledge loop for wind maintenance, from data sources through normalization, observation, correlation and detection, to a scenario generator, reasoning and knowledge, and a person who decides, with the results fed back. - Image: Diagram of a loop: data sources from field service, schedules, operations, weather, SOPs, finance and assets pass through data normalization, observations, correlation and detection, a scenario generator, reason and knowledge, to a person who decides; four colored keys beneath, from data ingress to deliver advisories. *A simplified view of bp's wind turbine maintenance.* ## People Block `kb-ops/people` · https://studiobing.com/davidbingham/work/kb-ops/#people The three user types from the primer: the Expert, the Doer and the Overseer. Writing them as industry-agnostic roles let the model hold across any operation, and the same three figures recur on the July workshop walls and the December journey map. - **The Expert** — These subject matter experts know their operational domain better than anyone. With decades of experience, they provide guidance on processes and technical issues to the business and their peers. Often close to retirement, their organizations are under threat of losing The Expert’s knowledge. — Problems - Image: Stick figure in a blue propeller hat holding a laptop with charts on its screen, under the title The Expert. - Codifying knowledge. - Collaborating with peers. - Scaling access to knowledge. - Receiving feedback & iterating. - **The Doer** — Doers take action when called upon by the organization. They are on-site and hands-on, performing necessary work while providing “human sensor” feedback into the system. The Doer’s industrial street-smarts complement the The Expert’s book-smarts to refine processes and associated actions. — Problems - Image: Stick figure in orange with a cap, a hand to its head and a tablet in the other hand, under the title The Doer. - Access to best practices. - Knowing task priority & urgency. - Contributing field insights. - **The Overseer** — Overseer’s are accountable for the overall business outcome and performance of the organization. They receive situational status updates and create broad plans to improve aspects of the operation. Overseers work with Experts to translate their plans into codified processes and actions. — Problems - Image: Stick figure in a red tie, a hand to its chin and the other pointing, under the title The Overseer. - Connecting strategy to tactics. - Managing information overload. - Keeping pulse on operations. ## Relationships Block `kb-ops/relationships` · https://studiobing.com/davidbingham/work/kb-ops/#relationships How the three roles meet around a concept: overseers and experts plan together, experts codify and review their work with colleagues, alerts reach the doer and others, and each trigger's feedback loops back into planning. - Image: Stick figures in three groups joined by arrows: an overseer and an expert; an expert between two smaller experts; a warning sign between a doer and a small overseer, with a dashed line running from the warning sign back over all three groups. - **Planning** — Overseers and Experts collaborate on translating business direction into operational processes that meet performance expectations. - **Codifying** — Experts associate data streams and write expressions to trigger under conditions. They test and review their work with expert colleagues. - **Alerting** — Individuals receive notifications when triggered. Doers perform associated actions while others are made aware of the situation. - **Iterating** — Each trigger records situational data and action feedback to inform planning and refine rule definitions. ## Model Block `kb-ops/model` · https://studiobing.com/davidbingham/work/kb-ops/#model The operational model card by card: the concept whole, then its data, its trigger and its action, built up in turn, each with its definition beneath. A concept is data plus trigger plus action, the shared nouns the company used before the product was debated. - **Concept** — A concept is the logical container for objects. Within Advanced Alerting, a concept is the file that an Expert creates, edits, and manages. A concept is able to exist as a “concept template”, with generic or temporary values until it is populated with active values as a “concept instance”. - Image: Diagram of a concept: a Data box with Variable and Source, a dark Trigger box with Expression and Evaluation, and an arrow down to a dark Action box with Notification, Scenario, Procedure, Calculation, API Call and a question mark. - **Data** — “Which information is important?” Connection to data sources are established for use across the concept. These connections are stored and represented in variables to simplify authoring. **Variable:** A plain-language term representing the current value of a connected data source. **Source:** The location a streaming data point, typically time series or event data. - Image: The concept diagram with only Data and its Variable and Source highlighted, Trigger and Action faded. - **Trigger** — “When should action be taken?” The trigger defines the circumstances under which actions should be taken. Both components are required for the concept to be valid. **Expression:** Expressions calculate as true or false based and optionally derive a stored value. **Evaluation:** Expressions are evaluated on a set schedule or a variable value change. - Image: The concept diagram with Data and Trigger, Expression and Evaluation, highlighted and Action faded. - **Action** — “What needs to be done?” One or more Actions are carried out when the Trigger evaluates as true. **Notification:** Send a message. **Procedure:** Perform a set of best practices. **Scenario:** Situational data purposeful to the concept. **Calculation:** Store variable data as a value for elsewhere. **API Call:** Connect to an external system. - Image: The concept diagram whole, with Data, Trigger and Action all highlighted. ## Setup Block `kb-ops/setup` · https://studiobing.com/davidbingham/work/kb-ops/#setup A worked example: a newspaper printer. The Overseer's goal and The Expert's rule of thumb become a concept's data and trigger: humidity, forecast, speed and job variables linked to their sources, an expression on humidity and speed, evaluated every 30 minutes. - Image: The Overseer says rain or shine we need to print and deliver tomorrow's newspapers; The Expert says if humidity gets too high, slow down printing to prevent paper jams. Beneath them a Data box of Variable and Source and a Trigger box of Expression and Evaluation, each pointing to its values: five variables, five sources, if Humidity > 70% and if Speed > 120, every 30 minutes. - The Expert defines variables “Humidity” and “Speed” as critical parameters. These are linked to streaming weather and machine control data sources. - The Expert defines variables “Humidity” and “Speed” as critical parameters. These are linked to streaming weather and machine control data sources. - A simple rule is created based on The Expert’s familiarity with paper’s response to humidity and the printing machine’s operating speeds. - The evaluation is set to reconsider the rule with current data every 30 minutes. - The Overseer sets his newspaper business goals and communicates to The Expert. ## Actions Block `kb-ops/actions` · https://studiobing.com/davidbingham/work/kb-ops/#actions The example's actions: Jim the overseer and Pat the doer to notify, three procedures for the production floor, and three scenario values to record, the forecast, the job and the count complete. - Image: The Expert says I need to notify people, keep an eye on conditions, and make adjustments to the production floor. Beneath, an Action box whose Notification points to Jim Overseer and Pat Doer, Procedure to set print speed to 70, close windows and doors, turn up air conditioner, and Scenario to record forecast, record job, count complete. - Pat is the technician responsible for the production floor. She will need handle the recommended procedures. Jim wants to be aware of changes to tomorrow’s delivery. - A list of best practice procedures guides The Doer towards the correcting the situation outlined in the concept. - The Expert notes a number of scenario parameters to assess. The forecast, which job is being printed, and an ongoing count of pieces completed. - The Expert adds the necessary Actions to occur if the Trigger condition becomes true. ## Run Block `kb-ops/run` · https://studiobing.com/davidbingham/work/kb-ops/#run The concept running: the evaluation comes round, the variables are stored, the expression is calculated, Jim and Pat are notified, Pat takes the procedures and The Expert reviews the scenario, each step numbered on the diagram. 1. Evaluation is reached. 2. Variables are stored. 3. Expression is calculated. 4. Notifications are sent. 5. Procedures are taken. 6. Scenario is reviewed. - Image: The concept with live values: Data with humidity 75%, the forecast, speed 130, the job and the count complete; the Trigger's evaluation every 30 minutes and its expression; the Action's scenario, notification to Jim and Pat and procedure; six numbered points from the evaluation to the warning signs at Jim and Pat and back to The Expert. ## Feedback Block `kb-ops/feedback` · https://studiobing.com/davidbingham/work/kb-ops/#feedback The Doer's feedback after the run: the printers are sensitive, so trigger earlier and adjust the procedure. The concept takes ratings of its effectiveness, rule updates and which procedures were taken, and the rule moves from speed over 120 to speed over 100. - Image: The Doer says the printers are sensitive, suggest triggering earlier and adjusting the procedure. Lines run to the concept: a thumbs down on concept effectiveness, the rule Speed > 120 struck through for Speed > 100, and procedures A thumbs down, B and C thumbs up. ## Library Block `kb-ops/library` · https://studiobing.com/davidbingham/work/kb-ops/#library Concepts kept in a library: The Expert makes a concept, places it in the library, and finds it again there. - Image: The Expert at a laptop makes a concept of data, trigger and action, which goes into a Library holding a second concept; a second Expert with a magnifying glass looks on. - Experts may create multiple Concepts for different purposes. - Concepts are stored in a Library. - The Library helps manage Concepts with groups, search, and filtering. ## Templates Block `kb-ops/templates` · https://studiobing.com/davidbingham/work/kb-ops/#templates Concept templates scale the model across an organization: an Expert's template goes into the library, and others create instances of it tied to their own data. - Image: The Expert at a laptop makes a concept template, which goes into the Library; a figure in a striped shirt takes the template and makes three concept instances from it. - Experts create Concept Templates to allow scaling definition across large organizations. - Concept templates stored in the library can be shared for others to access and generate concept instances. - Others find meaningful concept templates and create instances tied to their specific data. ## Rules Block `kb-ops/rules` · https://studiobing.com/davidbingham/work/kb-ops/#rules My first sketch of the rule builder, February 2022. Rules are built from an inserted spreadsheet function, an evaluation and a value, so an expert writes them in a syntax they already know, and the margin notes carry the reasoning. The construct survived unchanged into the hi-fi editor. - Image: Hand-drawn sketch of a rule builder: an if any rule is true then trigger line, two example rules, a searchable function palette and green margin notes. *Defining multiple rule conditions.* ## Backtest Block `kb-ops/backtest` · https://studiobing.com/davidbingham/work/kb-ops/#backtest The template backtest sketch, signed 7 February 2022. Before a rule is allowed to interrupt anyone, the expert binds its variables to historical tags, picks a date range and sees where it would have triggered. I designed the trust mechanism before the product. Beside it, the Data panel in two states, empty and bound, with Fred connected to wind speed and Wilma to rotation: how an expert connects a concept to data sources. Wind was the worked example six months before wind was the customer. - Image: Hand-drawn template backtest sketch with three numbered steps, a data picker, a date range and a line chart marked with a trigger point. — Creating a concept template backtest. - Image: Sketch of the Data panel in two states, empty and with Fred bound to wind speed and Wilma to rotation, beside a data picker. — Connecting variables to data sources. ## Flowchart Block `kb-ops/flowchart` · https://studiobing.com/davidbingham/work/kb-ops/#flowchart The service drawn end to end that autumn: install and configuration, creating a concept template, creating an instance, the rule triggering and the action performed. Existing alerts, data and expert knowledge feed the template at the start, and scenarios, notification responses and actions loop back as later inputs. The feedback loop is the structure, not a feature. - Image: A wide service flowchart under five stage headings, from install and configuration to action performed, with process boxes, data stores and stick-figure users, and feedback lines looping back to the start. *Concept creation and lifecycle diagram.* ## Wireframes Block `kb-ops/wireframes` · https://studiobing.com/davidbingham/work/kb-ops/#wireframes The v1 wireframe set whole: the screens of each stage of the service in sequence, under the theme get the data flywheel started, with the users who act at each step. - Image: A very wide sheet of green wireframes under stage headings, with persona figures, functionality notes over each screen and the v1 theme line at the top left. *Wireframes indicating needed content and affordances.* ## Screens title Block `kb-ops/screens-title` · https://studiobing.com/davidbingham/work/kb-ops/#screens-title The title over the hi-fi screens: high resolution user interfaces for desktop and mobile. High resolution user interfaces for desktop and mobile. ## Screens Block `kb-ops/screens` · https://studiobing.com/davidbingham/work/kb-ops/#screens The hi-fi screens under the Advanced Alerting name: the test results at full scroll, beside the library of drafts and published concepts and the notification e-mail on a phone. Fred and Wilma survive from the first sketch as variable names, and the published concepts carry effectiveness scores. - Image: A tall Advanced Alerting test results screen: a chart with triggers, then scenario recordings, notification contacts and procedure steps. - Image: Advanced Alerting library screen: a table of recent concepts, draft cards and colored published cards with point scores, with search filters on the right. - Image: A phone showing the branded Advanced Alerting e-mail from no-reply@aa.beyond.ai, headed Notification, with a View in Application button and a Beyond Limits footer. ## Release record Block `kb-ops/release-record` · https://studiobing.com/davidbingham/work/kb-ops/#release-record The public record of the release: the March 2024 press release launching the Hybrid AI Platform with KBOps as its knowledge component and PRE delivering alerts and actions, Frost & Sullivan's award naming KBOps, and the company's own account of its origin at NASA JPL and Caltech. - Record - Citation - **Hybrid AI Platform launched, with KBOps and PRE** — [Press release · 2024 — Accesswire: “Beyond Limits Introduces Its Breakthrough Hybrid AI Platform Delivering Unprecedented Resiliency and Efficiency for Mission Critical Operations”](https://finance.yahoo.com/news/beyond-limits-introduces-breakthrough-hybrid-142000685.html) - **Frost & Sullivan 2023 Global Enabling Technology Leadership Award** — [Press release · 2024 — PR Newswire: “Beyond Limits Recognized with Frost & Sullivan's 2023 Global Enabling Technology Leadership Award”](https://www.prnewswire.com/in/news-releases/beyond-limits-recognized-with-frost--sullivans-2023-global-enabling-technology-leadership-award-for-transforming-the-industrial-ai-solutions-industry-with-its-cutting-edge-hybrid-ai-technology-302055938.html) - **BeyondAI, from space to industry** — [Company page — BeyondAI: “Our Story – From Space to Industry”](https://beyond.ai/about/our-story) ## Lineage Block `kb-ops/lineage` · https://studiobing.com/davidbingham/work/kb-ops/#lineage One idea across three records, earliest first: the case-display patent of 2015, Asset Performance Management (2014–2015), and this project (2022). KBOps closes what the earlier work left open: the expert's rule, the doer's procedure, and the feedback between them. Lineage · earliest first 1. Patent · 2015 — [Case display](https://studiobing.com/davidbingham/patents/#apm-case-display) 2. 2014–2015 — [Asset Performance Management](https://studiobing.com/davidbingham/work/asset-performance-management/) 3. 2022 — **KBOps** (this page) - **AI:** 2, Ideas. AI helped with research, sources, brainstorming or structure. I wrote every word. The tiers: https://studiobing.com/davidbingham/writing/#ai