🧱 Pega Web Components

This is the local development page. Each component below is a standard <pega-*> custom element powered by React under the hood.

Persona Hero

Reimagine business outcomes while breaking nothing. Only Pega AI is grounded in best practices with governance built in – so you can continuously design, adapt, and grow your business without disruption. Build a Blueprint Explore the platform How do you want to innovate?

Hero Carousel (Variant A) (slotted children)

Reimagine business outcomes while breaking nothing. Only Pega AI is grounded in best practices with governance built in – so you can continuously design, adapt, and grow your business without disruption. Build a Blueprint Explore the platform

Hero Carousel (Variant B) (centered layout)

Reimagine business outcomes while breaking nothing. Only Pega AI is grounded in best practices with governance built in – so you can continuously design, adapt, and grow your business without disruption. Build a Blueprint Explore the platform

Customer Logos (slotted children)

Trusted by leading global organizations worldwide HSBC HSBC logo Citi Citi logo Allianz Allianz logo AEGON AEGON logo Cigna Cigna logo CVS Health CVS Health logo Vodafone Vodafone logo Cisco Cisco logo Siemens Siemens logo Google Google logo

Stacking Accordion

Digital self-service One Pega Platform. Four paths to becoming a modern AI enterprise. Workflow Automation Cut process time in half and free teams up for work that matters most. 76 Decrease in onboarding time See how HealthFirst did it Customer Service Reduce handle time per interaction, at enterprise scale. 80 Orders automated See how Citi did it Customer Engagement Drive measurable lift on every interaction, for every customer, across every channel. 40 Increase in channel revenue See how Wells Fargo did it Legacy Transformation Go from thousands of lines of legacy code to a cloud-ready prototype in weeks, not years. 50 Reduction in process lead times See how Deutche Bahn did it Digital engagement This is where ambition meets accountability, at enterprise scale Reimagine your business Reimagine your business with Pega Blueprintβ„’ Anyone can automate a process. Pega drives outcomes – with every decision grounded in your business rules, your compliance standards, and real-time context. Run it predictably Run it predictably with the market's most predictable AI agents Our AI agents don't just act. They each operate with context, compliance, and human oversight from the start. So you can orchestrate your agentic workforce end-to-end. Design for evolution Design for evolution with Pega's unique platform architecture With Pega Platform, AI is unified, predictable, and safe for mission-critical work. Our architecture is also key to unlocking scale and continuous evolution for your business. Connect everything Use any AI, any cloud, any data with Pega's model-agnostic, ecosystem-friendly approach Get the most out of the systems that work for your business. Pega's flexible platform approach lets you access and connect everything you have while making room for what's next. Blueprint Meet your reinvention engine Pega Blueprintβ„’ brings business and IT together in one AI-powered workspace, combining proven best practices and governance so your design-time innovations become confident, production-grade go-lives. Build a Blueprint

ROI Calculator V2

AI Cost Estimator Your AI is re-reading its own homework.
At every step. On your bill. LLM-orchestrated workflows don't just call agents β€” they reason through the entire workflow history before every single action. That context window compounds. So does the cost. Calculate your exposure See how it works How it works LLM-orchestrated workflows don't
just call agents β€” they re-reason everything. Before every single action, the orchestrator re-reads the entire workflow history to decide what to do next. That context window compounds with every step. Most platforms never mention this. 5-20Γ— LLM-orchestrated workflows cost 5 - 20Γ— more per run than Pega's targeted execution. And the gap compounds with every additional workflow step, as context windows grow and token usage accelerates. AI-native orchestration Re-reason at every step A master LLM re-reads the full workflow history at every step before dispatching the next action. By step 20, it's processing everything from steps 1–19 just to decide what step 20 should be. Token costs don't grow linearly β€” they grow quadratically. With Pega Deterministic execution,
targeted agents Pega separates the thinking from the doing. Deterministic orchestration handles the workflow. Targeted agents handle the judgment. You only pay LLM prices where LLMs are actually needed. AI Cost Reality Check How much are you
spending today? Configure your workflow below. Switch to Advanced for granular token and pricing controls. Simple estimate Advanced options Expert Start with a scenario β€” or set your own below Workflows per month workflows Total steps per workflow steps AI agent steps agent steps Show my annual savings Workflow configuration AI agent steps Total workflow steps Monthly volume (cases) Per agent call β€” Pega targeted step Input tokens (Pega step) Output tokens (Pega step) Per step β€” LLM orchestration Context growth / step Output tokens / step Token pricing ($ per million tokens) Input token price Output token price Pega platform cost Price per case ($) Calculate Savings Your estimate Here's what Pega
saves you. Without Pega β€” annual spend All steps sent to Claude Sonnet ($3/$15 per 1M) With Pega β€” annual spend Includes $0.60/case Pega platform cost Estimated annual savings Based on 10,000 workflows/month Β· 40 total steps Β· 28 agent steps % saved Talk to an expert See the data Estimates use the same underlying model in both Simple and Advanced modes: Pega cost = (agent steps Γ— scoped token cost) + platform fee; AI-native cost = Ξ£(step i) [2,000 + i Γ— context growth per step] input tokens + output tokens at every step. Default pricing: Claude Sonnet $3/M input Β· $15/M output. Pega platform fee: $0.60/case. All assumptions adjustable in Advanced mode. Estimates are illustrative. Visual proof Why AI-native orchestration
costs grow quadratically. Every step, the AI-native orchestrator re-reads the entire workflow history to decide what to do next. At step 20, it's processing everything from steps 1–19. The input token bill doesn't grow linearly β€” it grows quadratically. Pega's deterministic engine has no such overhead. Cumulative cost per workflow run β€” step by step 1,000 monthly cases Β· Claude Sonnet pricing Β· costs compound as context grows Pega (deterministic + targeted agents) AI-native (re-reasons every step) The chart plots cumulative cost in dollars step-by-step through a single workflow run. Pega's line rises only at agent steps; the orchestration line rises at every step and accelerates as context grows. Step Pega (targeted agents) LLM-orchestrated How we calculated this β€” full assumptions & methodology Full model β€” assumptions, token math & formula methodology All values reflect your current calculator inputs. Updates dynamically as you adjust settings above. Download CSV Print / Save PDF Input Assumptions Calculated Results Per-run comparison. Multiply by monthly volume for total cost. Formula methodology Complete the calculator above and click "Show my annual savings" to see your estimate. Token pricing sourced from provider API documentation, April 2026. Default pricing reflects Claude Sonnet ($3/M input Β· $15/M output). AI-native orchestration cost models context accumulation as an arithmetic series β€” the cost driver is quadratic with workflow length, not linear. Pega cost reflects targeted LLM calls only at designated agent steps, plus optional platform fee. All assumptions are adjustable. Estimates are illustrative. What counts as a workflow?
One end-to-end process your AI handles β€” a customer service case, a loan application, an onboarding request, a claims review.

Quick estimate: If your team handles ~200 cases a day, that's roughly 4,000/month. Total steps end-to-end
Every action in the workflow counts β€” data lookups, decisions, status updates, async waits, and AI agent calls. In an AI-native system, the orchestrator re-reads the full history at every one of these.

Typical range: Simple process β‰ˆ 10–20 Β· Enterprise case β‰ˆ 30–60 Steps that need AI judgment
Of your total workflow steps, how many actually require an LLM β€” classification, document analysis, drafting, decision-making? The rest are handled deterministically by Pega at near-zero token cost.

Quick guide: Typically 20–40% of total steps Β· A 40-step workflow might have 10–15 genuine AI agent steps What are AI agent steps? The number of steps inside your workflow where an LLM is actually called β€” decisions, classifications, drafting. Non-AI steps like database lookups or rule checks don't count.

Tip: If 28 of your 40 workflow steps involve AI reasoning, set this to 28. Total steps vs. agent steps The full length of your workflow end-to-end, including non-AI steps like data retrieval, rule evaluation, and system calls.

Example: A claims workflow might have 40 steps total, but only 28 of those call an LLM. How many cases per month? The total number of times this workflow runs in a month across all users or customers.

Quick estimate: 200 cases/day Γ— 22 working days β‰ˆ 4,400/month. Input tokens per Pega agent call The number of tokens sent to the model for each targeted Pega agent step. Because Pega locks in context before the run, this stays small and fixed β€” typically just the task prompt and relevant data.

Typical range: 500–3,000 tokens per call. Output tokens per Pega agent call The number of tokens the model returns for each targeted agent step. Pega's structured outputs keep this concise β€” usually a classification, a short decision, or a structured JSON blob.

Typical range: 100–800 tokens per call. Why does context grow? In LLM-orchestrated workflows, the model's conversation history grows with every step β€” each prior action, tool result, and response gets appended. This is what causes costs to compound.

Example: If each step adds ~2,000 tokens of history, by step 20 you're sending 40,000 tokens just in context. Output tokens per LLM step How many tokens the LLM generates in response at each orchestration step. This stays relatively constant per step, but you pay it every step β€” unlike Pega where only agent steps incur output cost.

Typical range: 200–1,500 tokens/step. What's an input token price? What you pay per million tokens sent to the model (your prompts, context, data). Input tokens are always cheaper than output tokens.

Reference prices (Apr 2026): GPT-4o ~$2.50 Β· Claude Sonnet ~$3.00 Β· Claude Opus ~$15.00 Β· Haiku ~$0.25 β€” all per 1M tokens. What's an output token price? What you pay per million tokens the model generates in response. Output tokens cost 3–5Γ— more than input tokens because generating text is computationally heavier.

Reference prices (Apr 2026): GPT-4o ~$10 Β· Claude Sonnet ~$15 Β· Claude Opus ~$75 Β· Haiku ~$1.25 β€” all per 1M tokens. Pega platform cost per case The Pega platform fee charged per workflow execution, on top of raw LLM token costs. This covers orchestration, routing logic, audit trails, and compliance tooling.

Set to $0 if you want to compare pure LLM token costs only, without factoring in platform licensing. Departmental operations 10,000 cases/mo Β· complex case management Β· 40 total steps Β· 28 agent steps Enterprise 100,000 cases/mo Β· multi-system orchestration Β· 50 total steps Β· 30 agent steps Scaled volumes 300,000 cases/mo Β· large-scale automated processing Β· 60 total steps Β· 35 agent steps PARAMETER YOUR VALUE NOTES WORKFLOW TOKEN PRICING PER AGENT CALL (PEGA TARGETED STEPS) LLM ORCHESTRATION (AI-NATIVE, PER STEP) AI agent steps Total workflow steps Monthly volume Input token price Output token price Pega platform cost Input tokens / call Output tokens / call Context growth / step Output tokens / step Steps where an LLM is actually invoked (Pega only) All steps end-to-end. AI-native re-reasons at every one Scales cost linearly for both architectures Claude Sonnet ~$3 Β· GPT-4o ~$2.50 Β· Opus ~$15 Typically 3-5Γ— input price Metered licensing β€” deterministic orchestration + audit trail System prompt + case data scoped to that step only Structured result, classification, or short decision Key lever β€” appended history grows quadratically. Conservative at 2K; real frameworks often 4K-8K Chain-of-thought + next-step decision per master agent call METRIC PEGA
(DETERMINISTIC + AGENTS) AI-NATIVE
(RE-REASONS EVERY STEP) SAVINGS W/ PEGA Input tokens / run Output tokens / run Total tokens / run Token cost / run Platform cost / run (Pega) All-in cost / run Monthly cost Annual cost Cost multiplier lower cost Pega cost per run = (AgentSteps Γ— InputTokens / 1M Γ— InputPrice)
  + (AgentSteps Γ— OutputTokens / 1M Γ— OutputPrice)
  + PlatformCostPerCase Only designated agent steps invoke an LLM. All other steps run deterministically at near-zero AI cost. Context is scoped to each individual call. AI-native orchestration input tokens per run = Ξ£ (step i = 0 to Nβˆ’1) [ 2,000 + i Γ— ContextGrowthPerStep ]
= N Γ— 2,000 + ContextGrowth Γ— N Γ— (Nβˆ’1) / 2 This is an arithmetic series. The NΓ—(Nβˆ’1)/2 term makes cost grow quadratically β€” not linearly β€” with workflow length. A workflow twice as long costs roughly four times as much to orchestrate. At step 20, the master agent is re-reading everything from steps 1–19 just to decide what step 20 should be. AI-native total cost per run = (OrchestratorInputTokens / 1M Γ— InputPrice)
  + (TotalSteps Γ— OutputTokensPerStep / 1M Γ— OutputPrice)
  + same targeted-agent costs as Pega The orchestration layer is pure overhead on top of the agent calls both architectures share. The gap widens with every step added to the workflow.