Our Personalization UI Promised Citations That Retrieval Could Not Keep
Review narrowed a product promise from fixed citations to a shared source pool with preferred passages, without claiming a new model-accuracy result
Reviewed by Victor Sineglazov on October 22, 2026.
Our initial personalization copy promised that language and depth could change while citations stayed the same. The retrieval policy could prefer passages from the reader's part of the book, so that promise was stronger than the system's behavior. Review corrected the wording before it became the interface's explanation of personalization.
A shared source pool does not freeze the selected passages
The same book and searched sources could participate while ranking favored material associated with a profession. That preference could change which passages reached the answer and therefore which citations appeared. Keeping the corpus stable did not guarantee an identical answer reference list. The final wording reflected the narrower mechanism: the same book and searched sources remained, with passages from the reader's part coming first. It described a preference without saying that the rest of the corpus had been excluded.
| Statement | Boundary it must respect |
|---|---|
| Same searched sources | Describes the participating source pool |
| Preferred part | Describes ordering or preference within retrieval |
| Same citations | Would require a stronger invariant |
| Answered only from one part | Would exclude material the implementation still permits |
A second sentence overstated exclusivity
The Practice Owner note initially described answers as coming from the first part. Review changed that to language expressing a leaning toward that part. The whole corpus still participated, so an exclusive-source claim would misdescribe an allowed result. This was not merely a softer marketing tone. The revised sentence changed the set of behaviors a reader could reasonably expect. A citation from another part should not look like a product defect caused by an interface promise the implementation never made.
The correction crossed several surfaces
Answer scope, onboarding and the Change profession flow all explained related behavior. Correcting one string would leave contradictory promises elsewhere. The change therefore had to propagate through the catalogs and the later profile flow.
A design-tool matrix still needed a matching update according to the recorded follow-up. We do not treat changed application strings as proof that every design artifact had been corrected. The source of truth for an implemented behavior and its remaining documentation work must stay distinguishable.
Review a promise against its mechanism
Our useful artifact is the statement-to-contract table above. For each sentence, identify whether it describes source eligibility, ranking, response style or an invariant, then ask which concrete implementation field or rule establishes that statement.
A passing translation-key check cannot answer this question. Nor can a well-formed role badge. The contradiction here required understanding how the backend selected passages and how the frontend explained that selection.
Turning the wording correction into a regression
The ledger records a specific contradiction found during the whole-branch review: the explanatory sentence promised fixed citations while the designed retrieval preference could change the selected passages. The owner kept retrieval and delegated the wording. That chronology matters because the resulting change was an explanation of existing allowed behavior, rather than a frontend change that froze the ranking.
We can restate the corrected contract without copying the private ledger's full translated sentences:
| Observation in a comparison | Consistent with the corrected promise? |
|---|---|
| Two professions search the same source pool | Yes, this is the shared scope |
| Their selected passages differ | Yes, preference can change selection |
| A preferred-part answer cites another part | Yes, preference is not exclusive eligibility |
| An old answer keeps its stored scope after Profile changes | Yes, new-request context does not relabel that answer |
In the last row, the wording meets the historical-answer contract without turning the two topics into one invariant. A changed citation list on a new request may be legitimate. A changed explanation of an unchanged saved response may be a display defect. A review that simply compares two screenshots for identical citations would confuse those cases.
Catalog tests pinned the owner-approved corrections. They are useful as a brake on accidentally reintroducing the old promise during a translation cleanup. They do not independently prove the retrieval algorithm: that still requires the service contract and the underlying selection behavior. Their job is to keep the interface from again stating a stronger invariant than the approved one.
Where a repaired string can still leave a broken promise
Responsibility for the matching design-tool rule remained with the designer in the record. An engineer reading that older matrix could otherwise restore the unchanged-citation language while believing they were repairing a discrepancy. Keeping the unresolved artifact named prevents a stale design note from silently outranking the implementation decision.
For a future review, the relevant comparison is between source eligibility, passage preference and the user-facing sentence on every affected surface. Benchmarking answer quality is a different activity. A correctly narrowed promise can be shipped without pretending that its wording is a model-quality result.
What the correction did not prove
The merged record includes the copy changes and local-cluster checking. Role-tagged benchmark questions were outside the recorded evaluation stage. We therefore do not claim that the correction improved model accuracy or proved every profession's answer quality.
Stas's contribution is the frontend promise and its integration across surfaces. Backend ranking belongs to the service work. Keeping that division explicit lets this case explain a product-language defect without claiming ownership of the retrieval algorithm.
FAQ
Quick answers to common questions about custom software development, pricing, process and technology.
Type to filter questions and answers. Use Topic to narrow the list.
Showing all 14
No matches
Try a different keyword, change the topic or clear filters
-
How long have you been in business?
Pharos Production has been in business since 2013, with over 13 years of experience in custom software development. During this time, we have delivered over 110 applications for 200+ clients across 28 industries, including FinTech, healthcare, crypto and e-commerce. We are rated 5/5 on Clutch based on 107 verified reviews (2026).
-
What services do you provide?
Pharos Production provides six core service categories: AI Development (LLM applications, AI agents, machine learning and computer vision), Blockchain and Web3 (smart contracts, DeFi, tokenization on Ethereum, Solana, TON and other chains), FinTech Development (payment platforms, digital banking, KYC and AML integration), Software Development (mobile apps, web platforms, database design, UI/UX), Security and QA (code audits, penetration testing, smart contract audits, manual and automated testing) and Consulting (architecture design, MVP validation, startup consulting).
-
Where is Pharos Production located?
Pharos Production is headquartered in Las Vegas, Nevada, USA (5348 Vegas Dr, Las Vegas, NV 89108), with an engineering office in Kyiv, Ukraine (44-B Eugene Konovalets Str. Suite 201, Kyiv 01133). We work with clients worldwide and provide remote collaboration across all time zones. Visit our contact page for directions and scheduling options.
-
How big is your team?
Pharos Production has a team of 90+ engineers, including software developers, blockchain specialists, QA engineers, DevOps experts, UI/UX designers, project managers and solution architects. Our founder, Dr. Dmytro Nasyrov, holds a PhD in Artificial Intelligence and leads the technical direction of all projects.
-
What types of customers do you serve?
We serve a wide range of clients, from startups and product companies to mid-sized enterprises and large institutions. Our clients include crypto exchanges, FinTech providers (like Pleenk), healthcare organizations, sportsbook operators (like Pro Gambling), e-commerce platforms and SaaS companies. Pharos Production has worked with 200+ clients across 28 industries since 2013, adapting engagement models to match each client's stage, whether it is MVP validation for a startup or enterprise-scale development for an established business.
-
How is a custom software development company different from an agency?
A custom software development company like Pharos Production assigns one dedicated engineering team that owns your product across multiple release cycles, instead of handing it off once a contract ends. Agencies more often rotate staff between clients and optimize for fast delivery over long-term product ownership.
Pharos Production keeps the same team on your codebase through 2-week sprints, so there is no re-onboarding cost each time you request a new feature.
-
How much does custom software development cost?
Custom software development costs vary based on project scope and complexity. At Pharos Production, typical project ranges are: MVP development ($10,000-$25,000), suitable for startups validating a product idea; full-fledged production ($25,000-$50,000), for established businesses scaling a proven concept; and full-cycle development ($50,000-$80,000+), for complex enterprise-grade systems. These ranges include architecture design, development, QA testing and deployment. Hourly rates range from $50 to $99 depending on role and seniority. Final pricing depends on technology stack, number of integrations and engagement model (staff augmentation, dedicated team or project outsourcing).
-
How long does it take to develop a custom software application?
Development timelines depend on scope and complexity. At Pharos Production, a typical MVP takes 2-4 months, a production-ready application takes 4-8 months and a complex enterprise system can take 8-12+ months. We use an agile methodology with 2-week sprints, delivering working increments after each sprint. Every sprint includes a retrospective, progress report and planning session for the next iteration. This approach ensures transparency and allows businesses to launch faster by prioritizing high-impact features first. Get a timeline estimate for your project.
-
What industries does Pharos Production serve?
Pharos Production serves 28 industries: FinTech, MiCA Compliance, Banking, Insurance, Crypto, Healthcare, Fitness, E-Commerce, Food & Restaurant, On-Demand, Manufacturing, Automotive, Energy, Oil & Gas, Supply Chain, Construction, Real Estate, Gaming, Streaming, Media, Telecom, Education, Aviation, Travel, Logistics, Marketing, Agriculture and Recommender Systems. Our deepest expertise is in FinTech, blockchain and healthcare, where we have delivered compliance-ready platforms (HIPAA, PCI DSS, GDPR) and high-load systems handling thousands of concurrent users. For the latest industry insights, read our guides on FinTech trends in 2026 and the Web3 technology stack.
-
Why hire a software development company instead of building in-house?
Hiring a software development company offers faster time-to-market, lower upfront costs and access to specialized expertise without long-term employment commitments. According to Deloitte's 2024 Global Outsourcing Survey, 57% of companies outsource software development to access skills they cannot hire internally.
Factor In-house team Software development company Time to assemble 3-6 months (recruiting + onboarding) 1-2 weeks Upfront cost High (salaries, benefits, equipment) Lower (project-based pricing) Specialized expertise Limited to who you can hire locally Access to 90+ engineers across blockchain, AI, FinTech Scalability Slow (each new hire takes months) Fast (scale up or down per sprint) Long-term commitment Full-time employment contracts Flexible engagement models Risk High if key engineers leave Company ensures continuity and knowledge transfer For businesses that need blockchain, AI or high-load architecture expertise, outsourcing to a specialized firm like Pharos Production reduces risk and accelerates delivery.
-
What projects does Pharos Production not take on?
Pharos Production focuses on mid-to-large custom software projects with budgets starting at $10,000. We do not take on template-based websites, WordPress theme customization or short-term contracts under one month. We also do not provide non-technical staffing (marketing, sales or design-only roles). Our strongest fit is blockchain, FinTech and healthcare projects where security, compliance and high-load architecture are critical. For smaller projects or MVPs under $10,000, we recommend exploring freelance platforms or no-code tools as a more cost-effective starting point.
-
Why does Pharos Production use agile methodology?
We use agile with 2-week sprints because it reduces the risk of building features that miss the mark. Each sprint ends with a working demo, a retrospective and a plan for the next iteration.
This means clients see progress every 14 days and can adjust priorities based on real results, not assumptions. We chose this approach after years of experience showing that rigid, fixed-scope contracts lead to scope creep, missed deadlines and products that do not match market needs by launch day.
-
When should you NOT hire a custom software development company?
Custom development is not the right choice in every situation. You should not hire a custom software company if: your problem is fully solved by an existing SaaS product (e.g. Shopify for e-commerce, Salesforce for CRM); your budget is under $10,000 and timeline is under 4 weeks; you need a simple landing page or marketing website (WordPress or Webflow is faster and cheaper); or you are still validating the idea and have not spoken to potential users yet.
In these cases, off-the-shelf tools or no-code platforms offer better ROI. Custom development makes sense when you need unique workflows, regulatory compliance, high-load architecture or competitive differentiation that packaged software cannot provide.
-
What kind of projects has Pharos Production delivered?
Here are three anonymized examples from our recent delivery history:
FinTech startup - payment platform (MVP)
Scope: mobile app + backend API with bank-grade encryption. Team: 4 engineers, 1 QA. Timeline: 10 weeks. Budget: $38,000. Result: launched on schedule, processed $2M+ in transactions within the first quarter.Healthcare provider - patient portal (Full product)
Scope: HIPAA-aligned web platform with EHR integration, appointment scheduling and telemedicine. Team: 6 engineers, 1 DevOps, 2 QA. Timeline: 6 months. Budget: $120,000. Result: 15,000+ active patients, zero compliance violations in two annual audits.Crypto exchange - trading engine (Complex)
Scope: high-load matching engine handling 50,000+ orders per second, multi-chain wallet infrastructure on Ethereum and Solana. Team: 8 engineers, 2 QA, 1 security auditor. Timeline: 11 months. Budget: $340,000. Result: 99.97% uptime, passed three independent security audits.See more projects: NoMoreBets, Pulse, Sagas, Gambit Stream and Pleenk. For the full portfolio, visit our case studies. Learn more about the technology behind these projects in our guide to stablecoins and crypto infrastructure.
Stas Rysin is the Lead Frontend Developer at Pharos Production. His work covers the design system, reader interfaces and administration workflows of a professional learning platform for aesthetic medicine.
